© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2636
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to assistance, actions, and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    French language text and phrases.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dorada
    -0.53
     arbeta
    -0.44
     muchacha
    -0.41
     néz
    -0.40
     admiten
    -0.40
     sû
    -0.39
     lyder
    -0.39
     traseiro
    -0.39
    çadas
    -0.38
     taxas
    -0.38
    POSITIVE LOGITS
    uxxxx
    0.69
    хьтан
    0.68
    zzleHttp
    0.66
    tagHelperRunner
    0.65
     wireType
    0.65
    ISupport
    0.63
    ChildScrollView
    0.63
    ThroughAttribute
    0.62
    RTSC
    0.61
    UnknownFieldSet
    0.60
    Activations Density 0.056%

    No Known Activations