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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11508
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of knowledge

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

    Information not previously known/available

    np_acts-logits-general · gemini-2.0-flash

    not captured, unavailable, not exist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.56
    RectangleBorder
    -0.54
     */,
    -0.49
    saraba
    -0.48
    >",
    -0.47
    fjspx
    -0.47
     MessageBoxIcon
    -0.46
    "",
    -0.46
    matchCondition
    -0.46
    QRect
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.38
     overlooked
    0.37
    XmlAccessType
    0.35
    XmlIgnore
    0.34
     ModelExpression
    0.32
    canestro
    0.32
     gaps
    0.31
     importación
    0.31
     belum
    0.31
     unseen
    0.30
    Activations Density 0.702%

    No Known Activations