© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3237
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfect" and related concepts like "ideal."

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

    the word "perfect" in various contexts.

    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
    adaptiveStyles
    -0.40
    Kjelder
    -0.40
    atimes
    -0.38
     Inscrivez
    -0.38
     useAppContext
    -0.37
     bileklik
    -0.37
     demikian
    -0.37
     /\.
    -0.36
    Rumble
    -0.35
     khusus
    -0.35
    POSITIVE LOGITS
    Perfect
    1.21
     Perfect
    1.18
     perfect
    1.14
    perfect
    1.13
     PERFECT
    1.13
    PERFECT
    1.12
     perfecto
    0.92
     imperfection
    0.92
     imperfect
    0.92
    perfectly
    0.91
    Activations Density 0.088%

    No Known Activations