Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11947
    Prev
    Next
    INDEX
    Explanations

    structured annotations and formatting styles in the text

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

    Code diff headers or separators

    np_acts-logits-general · gemini-2.0-flash

    code separators and tables

    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
    Sprintf
    -0.50
     moindre
    -0.49
     demur
    -0.49
    bitField
    -0.47
     litio
    -0.46
    abetes
    -0.46
    protoimpl
    -0.46
    ={`/
    -0.45
     createSprite
    -0.45
    siamo
    -0.45
    POSITIVE LOGITS
    multicolumn
    1.26
    RectangleBorder
    0.87
    ftagPool
    0.83
    principalTable
    0.82
     onPostExecute
    0.81
    enumi
    0.79
    \{\\
    0.79
    enumii
    0.76
     مشين
    0.76
     ſind
    0.68
    Activations Density 0.003%

    No Known Activations