© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1065
    Prev
    Next
    INDEX
    Explanations

    pieces or fragments of items, particularly in a scientific or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.50
    таратура
    -0.49
     surla
    -0.42
    VersionUID
    -0.41
    ArrowToggle
    -0.41
    AutoScaleMode
    -0.40
    Nuorodos
    -0.39
    帖最后由
    -0.38
    setViewName
    -0.38
    keyColumn
    -0.36
    POSITIVE LOGITS
     pieces
    2.50
     fragments
    2.36
     Pieces
    2.14
     piece
    2.06
     fragment
    2.02
     chunks
    1.94
     Fragments
    1.89
     segments
    1.88
    Pieces
    1.85
    pieces
    1.84
    Activations Density 0.968%

    No Known Activations