© 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. 4382
    Prev
    Next
    INDEX
    Explanations

    terms associated with errors or mistakes

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

    the word "wrong" and related negative judgment terms.

    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
    apatalk
    -0.34
    PRNewswire
    -0.32
     gawas
    -0.32
    lardır
    -0.31
    textLabel
    -0.30
    Nation
    -0.27
     sinn
    -0.27
    Naphthalene
    -0.27
    Bay
    -0.27
    fina
    -0.27
    POSITIVE LOGITS
    neous
    0.69
     Wrong
    0.65
    Wrong
    0.63
    wrong
    0.63
     wrong
    0.60
     DIRECTION
    0.59
    WRONG
    0.58
    rungsseite
    0.58
     مشين
    0.57
     WRONG
    0.56
    Activations Density 0.201%

    No Known Activations