© 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. 6924
    Prev
    Next
    INDEX
    Explanations

    various types of opening and closing parentheses, brackets, and quotation marks

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

    Code or code-like syntax

    np_acts-logits-general · gemini-2.0-flash

    opening parenthesis or bracket inside code

    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
     
    -0.77
     E
    -0.64
     Иль
    -0.63
     G
    -0.61
     seen
    -0.61
     U
    -0.59
     ne
    -0.59
    اس
    -0.59
     to
    -0.59
     L
    -0.59
    POSITIVE LOGITS
     للمعارف
    1.54
     $("<
    1.10
     Aoki
    1.04
    antMatchers
    1.02
    ={({
    1.01
     __('
    1.01
    ","","
    1.00
     doInBackground
    1.00
    =$((
    0.98
     Judah
    0.97
    Activations Density 0.172%

    No Known Activations