© 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. 11-GEMMASCOPE-RES-16K
    6. 8559
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability and capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.60
    Lähteet
    -0.55
    isait
    -0.54
     autorytatywna
    -0.54
     Leith
    -0.54
    Geplaatst
    -0.52
     biais
    -0.52
    elry
    -0.52
     Numerology
    -0.52
    setAction
    -0.51
    POSITIVE LOGITS
     afford
    0.82
     can
    0.79
     Can
    0.78
     توانند
    0.76
    وانید
    0.76
    Can
    0.74
     تواند
    0.74
    reasonably
    0.74
    easily
    0.73
     能
    0.73
    Activations Density 0.240%

    No Known Activations