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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 491
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect hypocrisy and criticism of political discourse

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

    discourse that dismisses or undermines claims with empty rhetoric and insincerity.

    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
     mó
    -0.34
    isNameExpr
    -0.34
     sá
    -0.32
    本線
    -0.32
     ats
    -0.31
    licant
    -0.30
    ces
    -0.30
    endmodule
    -0.30
    plain
    -0.29
    mains
    -0.28
    POSITIVE LOGITS
     talk
    1.35
     rhetoric
    1.30
    talk
    1.10
     professed
    1.05
     TALK
    1.05
     Talk
    1.04
     promises
    1.04
    Talk
    1.00
     talked
    0.98
     promesas
    0.95
    Activations Density 0.521%

    No Known Activations