© 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. 9-GEMMASCOPE-RES-16K
    11. 1744
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.85
    \"");
    -0.82
     Audiodateien
    -0.80
     تانيه
    -0.79
     мѣ
    -0.77
    \}\\
    -0.74
    ++)
    -0.73
    [])
    -0.73
    %");
    -0.71
    setOutput
    -0.71
    POSITIVE LOGITS
    May
    0.71
     doInBackground
    0.70
     hasbro
    0.69
    :✨
    0.66
    Can
    0.66
     dieux
    0.65
    CAN
    0.64
     Canva
    0.63
     makeStyles
    0.62
     Hasbro
    0.62
    Activations Density 0.242%

    No Known Activations