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

    Neuronpedia

    Jacobian LensNEW
    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. 5848
    Prev
    Next
    INDEX
    Explanations

    structured scientific procedures and durations

    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
     Photocase
    -0.38
     fechas
    -0.34
     Ten
    -0.34
    JsonInclude
    -0.33
     rosto
    -0.32
    Witam
    -0.31
    ンバー
    -0.31
     viewWillAppear
    -0.31
     année
    -0.31
     fêtes
    -0.31
    POSITIVE LOGITS
     hour
    2.77
     hours
    2.45
     Hour
    2.34
    hour
    2.33
    Hour
    2.25
     HOUR
    2.20
     Hours
    2.08
    hours
    2.05
    Hours
    2.02
     HOURS
    1.93
    Activations Density 0.599%

    No Known Activations