© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4958
    Prev
    Next
    INDEX
    Explanations

    references to user interface elements and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    web development or programming code-related terms and tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    UI/software terms indicating creation or editing actions—especially starting or composing new items, records, or forms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    function/method definitions and UI element creation in code, particularly for forms and buttons.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataSnapshot
    -0.51
    AndEndTag
    -0.51
     NKC
    -0.48
    اریخ
    -0.47
     Bioaccumulative
    -0.46
    setopt
    -0.45
     Administrativna
    -0.44
     Alamofire
    -0.44
    matchCondition
    -0.43
     ujednoznacz
    -0.42
    POSITIVE LOGITS
    EDEFAULT
    0.43
    AntiForgeryToken
    0.42
    CreateModel
    0.39
     Towards
    0.38
    StoryboardSegue
    0.37
    Towards
    0.36
     Credit
    0.36
    ContentValues
    0.36
    PreExecute
    0.36
    addCriterion
    0.35
    Activations Density 0.040%

    No Known Activations