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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7664
    Prev
    Next
    INDEX
    Explanations

    command-line options and flags in a script or code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.45
    PointerException
    -0.45
     Reihenfolge
    -0.44
    tagHelperRunner
    -0.43
     abbraccio
    -0.42
     ſche
    -0.40
    didSet
    -0.40
     hiér
    -0.40
     pikir
    -0.40
     braços
    -0.40
    POSITIVE LOGITS
    LabelTagHelper
    0.48
    flags
    0.48
    rawDesc
    0.47
    kháu
    0.46
     flags
    0.44
    avy
    0.42
    Flags
    0.42
     bParam
    0.42
     autorytatywna
    0.41
    Географиясе
    0.40
    Activations Density 0.216%

    No Known Activations