© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 1343
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to DNA damage and repair mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    damage and repair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sträger
    -0.46
     Tern
    -0.40
    vänt
    -0.38
    accordo
    -0.38
     memoized
    -0.36
     pleasing
    -0.36
    InjectAttribute
    -0.35
     StringVar
    -0.35
    Бележки
    -0.35
    tahankan
    -0.34
    POSITIVE LOGITS
     repair
    0.60
    Repair
    0.53
     damage
    0.53
    repair
    0.52
     Repair
    0.51
     DAMAGE
    0.50
    Damage
    0.49
     REPAIR
    0.48
    #+#
    0.48
     Damage
    0.47
    Activations Density 0.061%

    No Known Activations