© 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. 0-GEMMASCOPE-RES-16K
    11. 9556
    Prev
    Next
    INDEX
    Explanations

    the presence of specific codes or identifiers, particularly related to formats or properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.82
    IsMutable
    -0.76
    parsedMessage
    -0.70
     informée
    -0.70
     Audiodateien
    -0.67
    enterOuterAlt
    -0.64
    ніципа
    -0.63
    DockStyle
    -0.63
    HideFlags
    -0.61
    évaluateur
    -0.60
    POSITIVE LOGITS
    ef
    0.78
     highlighting
    0.71
     highlights
    0.70
     highlighted
    0.68
     longer
    0.67
     focused
    0.64
    EF
    0.64
    highlighted
    0.61
    focus
    0.60
    Ef
    0.60
    Activations Density 0.347%

    No Known Activations