© 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. 3-GEMMASCOPE-RES-16K
    6. 9250
    Prev
    Next
    INDEX
    Explanations

    actions related to learning and using knowledge or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.61
    Портал
    -0.56
    findpost
    -0.56
    InjectAttribute
    -0.55
    Diweddarwch
    -0.54
    
    -0.46
     surla
    -0.45
    verwijspagina
    -0.44
    XtraReports
    -0.43
    RTGC
    -0.43
    POSITIVE LOGITS
     insanlar
    0.47
     Avez
    0.47
     investors
    0.47
     Individuals
    0.47
     individuals
    0.46
    tieron
    0.45
    Individuals
    0.45
     Voters
    0.45
    consumers
    0.44
     usuarios
    0.44
    Activations Density 1.046%

    No Known Activations