© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107768
    Prev
    Next
    INDEX
    Explanations

    references to performances by actors and actresses in films

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

    acting and performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.58
     <<<<<<<<<<<<<<
    -0.51
    SharedCtor
    -0.45
    ronpa
    -0.41
     indépend
    -0.40
     allAfrica
    -0.40
    StructEnd
    -0.40
     ouverture
    -0.39
     rangement
    -0.39
     Numerade
    -0.39
    POSITIVE LOGITS
     actor
    0.71
     actors
    0.68
     Actors
    0.66
     cast
    0.64
    Actors
    0.64
     casting
    0.62
     Actor
    0.62
    Actor
    0.60
    演員
    0.57
    Casting
    0.57
    Activations Density 0.247%

    No Known Activations