© 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. 15928
    Prev
    Next
    INDEX
    Explanations

    references to events, organizations, or specific gatherings

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

    welcoming introductory messages or headers that introduce a website, event, or community.

    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
    principalColumn
    -0.62
    دانشنامهٔ
    -0.55
    ThroughAttribute
    -0.53
    Демографія
    -0.53
    stateProvider
    -0.47
     soort
    -0.46
     snippetHide
    -0.46
    zzar
    -0.43
    SharedDtor
    -0.43
    CloseOperation
    -0.42
    POSITIVE LOGITS
     wonderful
    0.54
     inaugural
    0.52
     #
    0.47
     fabulous
    0.46
     magnificent
    0.45
     amazing
    0.45
     lovely
    0.45
     upcoming
    0.45
    tagPool
    0.44
     wonderfully
    0.44
    Activations Density 0.444%

    No Known Activations