© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8746
    Prev
    Next
    INDEX
    Explanations

    numerical references or citations within the text

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

    Numbers followed by a semicolon or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    citation numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustra
    -0.48
    /#{
    -0.47
     ByteArray
    -0.46
     rond
    -0.46
     frame
    -0.43
     \"%
    -0.43
    CppMethod
    -0.43
    Gweler
    -0.42
    bkz
    -0.42
     or
    -0.42
    POSITIVE LOGITS
    VersionUID
    0.82
    脚注の使い方
    0.77
    RunWith
    0.68
     للمعارف
    0.66
     Lordships
    0.64
     Humanos
    0.63
     createState
    0.63
     Roskov
    0.61
    StoryboardSegue
    0.58
    WEBPACK
    0.57
    Activations Density 0.114%

    No Known Activations