© 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. 7-GEMMASCOPE-RES-16K
    11. 11554
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and their usage in sentences, indicating purpose and action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.81
    ImageContext
    -0.75
    ніципалі
    -0.69
    gonic
    -0.69
     Balk
    -0.68
    RemoteException
    -0.68
     ролях
    -0.67
    UnusedPrivate
    -0.65
    FieldBuilder
    -0.65
     ")");
    -0.64
    POSITIVE LOGITS
    To
    1.49
     To
    1.43
     Toh
    1.00
     TO
    0.91
     Чтобы
    0.86
    TO
    0.83
    to
    0.78
    setTo
    0.77
     Toi
    0.76
     Unto
    0.72
    Activations Density 0.151%

    No Known Activations