© 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. 27-GEMMASCOPE-RES-16K
    11. 9491
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.50
    2
    -0.44
     
    -0.44
    <em>
    -0.43
     in
    -0.42
    1
    -0.41
     actor
    -0.40
    d
    -0.40
    <strong>
    -0.40
    6
    -0.40
    POSITIVE LOGITS
    featureID
    0.95
    UnusedPrivate
    0.84
     queſta
    0.83
    OGND
    0.82
    oredCriteria
    0.80
    isContained
    0.79
    PerformLayout
    0.77
     Chwiliwch
    0.76
    ConstraintMaker
    0.76
     Numerade
    0.73
    Activations Density 0.626%

    No Known Activations