© 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. 13-GEMMASCOPE-RES-16K
    6. 3088
    Prev
    Next
    INDEX
    Explanations

    instances of speech or reporting statements from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.59
    Datuak
    -0.56
    oughly
    -0.54
    Đây
    -0.54
     zupeł
    -0.53
    byes
    -0.53
    Portály
    -0.52
     primas
    -0.52
    PreAuthorize
    -0.51
    endios
    -0.51
    POSITIVE LOGITS
     suggests
    0.73
     also
    0.70
     Normdatei
    0.64
     suggested
    0.64
     suggest
    0.63
     then
    0.62
     furthermore
    0.62
     cautioned
    0.59
     suggesting
    0.58
     moreover
    0.56
    Activations Density 0.257%

    No Known Activations