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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 11851
    Prev
    Next
    INDEX
    Explanations

    code or programming language syntax.

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

    programming code snippets containing specific functions or data structures.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    array declarations and initializations in programming code.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Brackets, braces, or backslashes followed by certain tokens

    np_acts-logits-general · gemini-2.0-flash

    set difference followed by brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     []);
    -0.56
    oda
    -0.49
    ([
    -0.49
    ([[
    -0.48
    EClass
    -0.48
    kata
    -0.46
     markets
    -0.46
     market
    -0.45
     Архивировано
    -0.44
    continue
    -0.44
    POSITIVE LOGITS
     $\{
    0.93
     \{
    0.92
     {'
    0.84
    =\{
    0.81
     {"
    0.81
    \{
    0.81
    $\{
    0.80
    }=\{
    0.79
     $\{\
    0.74
    {'
    0.74
    Activations Density 0.610%

    No Known Activations