© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7131
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online academic resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.80
    RTEX
    -0.69
     queſta
    -0.63
    OCCURRED
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    béco
    -0.59
    KURZBESCHREIBUNG
    -0.59
    EndGlobalSection
    -0.56
    zzleHttp
    -0.54
    adaptiveStyles
    -0.50
    POSITIVE LOGITS
    ']}
    0.41
    ()">
    0.39
    MathML
    0.35
    "]}
    0.35
     "..\..\..\
    0.34
    }}}{
    0.34
     BUL
    0.34
    ])){
    0.34
    ()>
    0.33
     quedaba
    0.33
    Activations Density 0.635%

    No Known Activations