© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15100
    Prev
    Next
    INDEX
    Explanations

    terms related to technical descriptions and specifications in scientific and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.70
     (
    -0.69
    ,
    -0.64
     and
    -0.60
    </strong>
    -0.57
    ;
    -0.56
    ↵↵
    -0.55
     &
    -0.54
     or
    -0.53
     -
    -0.51
    POSITIVE LOGITS
    <bos>
    1.21
     myſelf
    1.19
     betweenstory
    1.14
     nakalista
    1.11
     createState
    1.11
     initComponents
    1.08
     nahilalakip
    1.07
    LookAnd
    1.06
     itſelf
    1.05
     jsPsych
    1.04
    Activations Density 4.681%

    No Known Activations