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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13736
    Prev
    Next
    INDEX
    Explanations

    instances of human actions or errors related to procedures and interactions

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

    Follows punctuation in varied contexts

    np_acts-logits-general · gemini-2.0-flash

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     beginnetje
    -0.54
     ProtoMessage
    -0.45
    findpost
    -0.45
     ComVisible
    -0.42
    pushFollow
    -0.42
    MLLoader
    -0.42
    CloseOperation
    -0.41
    InputTagHelper
    -0.41
    IndentedString
    -0.41
    EDEFAULT
    -0.40
    POSITIVE LOGITS
    出版年
    0.42
    webElementXpaths
    0.40
    avi
    0.40
     berdua
    0.39
    IBOutlet
    0.38
    wapV
    0.37
    Sweet
    0.37
    Наводи
    0.36
    AP
    0.35
    Bir
    0.35
    Activations Density 0.671%

    No Known Activations