© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9815
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knock" and its variations

    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
    AccessorTable
    -0.49
     informée
    -0.41
    SharedCtor
    -0.39
     iprot
    -0.39
    webElement
    -0.38
    ChildScrollView
    -0.35
     stimmt
    -0.35
     désolés
    -0.34
    multline
    -0.34
    elemField
    -0.33
    POSITIVE LOGITS
    knock
    0.72
     Kn
    0.70
     knock
    0.70
    Kn
    0.68
    Knock
    0.68
     KN
    0.65
     BUL
    0.64
    KN
    0.63
    kn
    0.61
     kn
    0.59
    Activations Density 2.037%

    No Known Activations