© 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 EvalsExportsinterp-engineNEWAPI 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. 10887
    Prev
    Next
    INDEX
    Explanations

    affirmative responses in a dialogue context

    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
    OGND
    -0.46
     transfieras
    -0.43
     Мексичка
    -0.37
    oplayer
    -0.35
    vician
    -0.35
    Geplaatst
    -0.34
    んだよね
    -0.33
    みんなの
    -0.33
    だよね
    -0.33
    epy
    -0.32
    POSITIVE LOGITS
     sir
    2.20
    Sir
    2.02
     Sir
    1.99
    sir
    1.78
     SIR
    1.60
    SIR
    1.56
     Sirs
    1.34
     madam
    1.34
     Madam
    1.20
     senhor
    1.20
    Activations Density 0.306%

    No Known Activations