© 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. 22-GEMMASCOPE-RES-16K
    6. 6400
    Prev
    Next
    INDEX
    Explanations

    code-related structures and comments

    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
     plainte
    -0.52
     &___
    -0.48
    iodía
    -0.45
     Савезне
    -0.44
     Macle
    -0.43
    insula
    -0.43
    Glej
    -0.42
     Nachbarn
    -0.41
     yyb
    -0.41
     Ärz
    -0.41
    POSITIVE LOGITS
    MessageOf
    0.43
    ContentAlignment
    0.41
    rungsseite
    0.40
     pylint
    0.38
     eslint
    0.37
    matchCondition
    0.37
     snippetHide
    0.37
     للاسماء
    0.37
    IContainer
    0.36
     समीक्षक
    0.36
    Activations Density 0.144%

    No Known Activations