© 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. 35-GEMMASCOPE-RES-16K
    6. 8241
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to linearity and transformations

    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
    tinyos
    -0.60
     automatiques
    -0.50
     départements
    -0.49
    JvmStatic
    -0.49
     AppModule
    -0.49
    unmodifiable
    -0.47
     BrowserModule
    -0.46
    AnchorStyles
    -0.46
     πρά
    -0.46
    endmodule
    -0.45
    POSITIVE LOGITS
     q
    0.35
    ξ
    0.34
    q
    0.33
    Q
    0.32
    =:
    0.32
     ξ
    0.32
    nitus
    0.32
     lantern
    0.32
     denoted
    0.31
     locator
    0.31
    Activations Density 3.710%

    No Known Activations