© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8960
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and their associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     never
    -0.49
     Never
    -0.45
    never
    -0.41
     should
    -0.39
    Never
    -0.38
     nunca
    -0.38
     Easily
    -0.35
     gerne
    -0.35
     volon
    -0.34
     onBind
    -0.33
    POSITIVE LOGITS
     contend
    0.89
     estekak
    0.80
    才行
    0.76
     necessariamente
    0.71
     worry
    0.69
     deal
    0.68
    MLLoader
    0.67
    addContainerGap
    0.66
    resort
    0.64
     decide
    0.63
    Activations Density 0.256%

    No Known Activations