© 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. 16-GEMMASCOPE-RES-16K
    6. 13323
    Prev
    Next
    INDEX
    Explanations

    JavaScript event handlers related to click events on document elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.84
     myſelf
    -0.81
     ſind
    -0.76
     MainAxisSize
    -0.74
    AddTagHelper
    -0.73
    rungsseite
    -0.70
     nahilalakip
    -0.69
    ſelf
    -0.69
    ImageContext
    -0.69
    ſelves
    -0.69
    POSITIVE LOGITS
    addEventListener
    0.49
    setOnAction
    0.40
     daily
    0.40
     "
    0.40
     follow
    0.39
     word
    0.38
     t
    0.37
     platform
    0.35
     to
    0.35
    2
    0.35
    Activations Density 0.072%

    No Known Activations