© 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. 101621
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to map entries and their manipulation in a data structure context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    EndGlobalSection
    -0.46
    ioare
    -0.45
    itsubishi
    -0.42
     capuz
    -0.42
     tracción
    -0.42
     fría
    -0.41
     pinulongan
    -0.41
     neuve
    -0.40
     abstrato
    -0.40
     nonUne
    -0.40
    POSITIVE LOGITS
    entrySet
    1.22
    AccessorTable
    0.52
    ValuePair
    0.49
    KeyValuePair
    0.48
    complexType
    0.46
    InitStruct
    0.45
     estekak
    0.45
     ModelExpression
    0.44
    AXB
    0.44
    AsUp
    0.43
    Activations Density 0.005%

    No Known Activations