Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14798
    Prev
    Next
    INDEX
    Explanations

    references to website evaluations and redesign processes

    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
    setVerticalGroup
    -0.58
     BorderSide
    -0.52
    Personensuche
    -0.50
     utafitiHapana
    -0.50
    .*")]
    -0.50
     hatch
    -0.49
     ModelExpression
    -0.47
     getItemId
    -0.47
    DECLARE
    -0.46
    ValueStyle
    -0.46
    POSITIVE LOGITS
     bisherigen
    0.64
     old
    0.59
    旧
    0.56
    เดิม
    0.56
    舊
    0.55
    old
    0.53
     旧
    0.53
     vieja
    0.52
     старый
    0.52
     oldValue
    0.51
    Activations Density 0.564%

    No Known Activations