© 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. 31-GEMMASCOPE-RES-16K
    11. 16171
    Prev
    Next
    INDEX
    Explanations

    references to media formats and programming changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases involving choosing or selecting one option in favor of another.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    polazione
    -0.34
    RegistryLite
    -0.32
     atra
    -0.32
     constriction
    -0.30
    就行了
    -0.29
    ほら
    -0.29
     Corre
    -0.29
    看看
    -0.28
     CORRECT
    -0.28
     chất
    -0.27
    POSITIVE LOGITS
     favour
    2.36
     favor
    2.34
     favoring
    1.90
    favor
    1.84
     Favor
    1.77
     favors
    1.73
     FAVOR
    1.66
     favore
    1.63
     favours
    1.62
    Favor
    1.61
    Activations Density 0.398%

    No Known Activations