© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7860
    Prev
    Next
    INDEX
    Explanations

    names and references associated with film production and cast members

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

    names of people and production companies associated with films.

    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
    额
    -0.28
    ListActivity
    -0.26
    WTA
    -0.24
    >(_
    -0.24
    ี้ย
    -0.23
     essi
    -0.23
    ʺ
    -0.23
    ài
    -0.23
     ô
    -0.22
     Bethany
    -0.22
    POSITIVE LOGITS
    istoitu
    0.78
    GOTREF
    0.75
     Bachchan
    0.72
     AssemblyVersion
    0.70
     resourceCulture
    0.70
    bootstrapcdn
    0.68
    Chham
    0.68
     Италијани
    0.68
     ffilm
    0.68
    LEncoder
    0.66
    Activations Density 0.063%

    No Known Activations