© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 110767
    Prev
    Next
    INDEX
    Explanations

    references to challenges within the entertainment industry and the support systems for those involved in it

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

    showbiz and actors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    دانشنامهٔ
    -0.59
     onBind
    -0.49
    +#+
    -0.49
    HomeAsUpEnabled
    -0.46
    ScopeManager
    -0.45
     personalización
    -0.44
    MessageOf
    -0.44
     INTERESAR
    -0.44
     verheiratet
    -0.43
    Przypisy
    -0.42
    POSITIVE LOGITS
     showbiz
    1.22
     Hollywood
    1.18
    Hollywood
    1.04
     hollywood
    0.97
     entertainment
    0.96
     Actors
    0.93
     filmmaking
    0.93
    LLYWOOD
    0.91
     Entertainment
    0.88
    hollywood
    0.84
    Activations Density 0.069%

    No Known Activations