© 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. 24-GEMMASCOPE-RES-16K
    11. 12489
    Prev
    Next
    INDEX
    Explanations

    words associated with reasoning and factors influencing decisions

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

    Follows words indicating a justification or explanation

    np_acts-logits-general · gemini-2.0-flash

    listing reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thương
    -0.41
    ürme
    -0.40
    XmlSchema
    -0.31
    PAIGN
    -0.31
    ionic
    -0.31
    /**/
    -0.30
     quelconque
    -0.30
    ologists
    -0.30
    OGND
    -0.29
    CEED
    -0.29
    POSITIVE LOGITS
    +#+#
    0.69
    IntoConstraints
    0.64
    ConstraintMaker
    0.63
    rungsseite
    0.61
    webElementXpaths
    0.60
    richTextPanel
    0.59
    enterOuterAlt
    0.56
    parsedMessage
    0.56
     nakalista
    0.55
     चीज़ों
    0.55
    Activations Density 0.418%

    No Known Activations