© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7599
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and references to scientific or academic work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocino
    -0.57
    •••
    -0.50
    ••
    -0.49
    ··
    -0.46
    BeforeMethod
    -0.44
     •
    -0.43
    いれば
    -0.43
    حياته
    -0.41
     trefoil
    -0.40
    法
    -0.40
    POSITIVE LOGITS
    حوالہ
    0.63
    titleMargin
    0.57
    entieth
    0.57
    Zal
    0.55
     Rasmus
    0.54
     GenerationType
    0.53
    URLException
    0.52
    runOnUiThread
    0.52
    SerializedName
    0.52
    onedDateTime
    0.50
    Activations Density 0.702%

    No Known Activations