© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8658
    Prev
    Next
    INDEX
    Explanations

    methods related to manipulating data structures, particularly lists and arrays

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

    list and array manipulation

    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
    󠁢
    -0.58
     UIImage
    -0.55
     queſta
    -0.52
    esModule
    -0.49
    SpringRunner
    -0.49
     Jefus
    -0.48
    isShowing
    -0.48
    RunWith
    -0.47
    AutoScaleMode
    -0.46
    centralwidget
    -0.43
    POSITIVE LOGITS
    splice
    1.22
     splice
    0.60
    arraycopy
    0.59
    bindValue
    0.55
    addGap
    0.50
    DeleteMapping
    0.45
    RemoveAt
    0.44
    basicConfig
    0.42
    Попис
    0.41
    AlterField
    0.40
    Activations Density 0.004%

    No Known Activations