© 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. 10-GEMMASCOPE-RES-16K
    11. 12330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.81
    almaz
    -0.80
    เอง
    -0.74
     Gales
    -0.73
     zijne
    -0.72
    ollection
    -0.72
     gethan
    -0.70
    Komentar
    -0.69
     saisir
    -0.69
     uyt
    -0.69
    POSITIVE LOGITS
    Gotta
    1.08
     gotta
    1.04
     Gotta
    1.00
     must
    0.94
     be
    0.93
    zzleHttp
    0.85
    gotta
    0.77
     needs
    0.76
    icoot
    0.76
    Must
    0.76
    Activations Density 0.105%

    No Known Activations