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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116868
    Prev
    Next
    INDEX
    Explanations

    terms related to hauling and towing activities

    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
    FunctionFlags
    -0.54
    ponses
    -0.52
    WebControls
    -0.49
     Aps
    -0.49
    Jeografia
    -0.48
     nakalista
    -0.48
    XmlType
    -0.48
    CppMethod
    -0.48
    endroit
    -0.47
    Notae
    -0.47
    POSITIVE LOGITS
     Haul
    1.01
    haul
    0.95
     haul
    0.87
     hauling
    0.81
     hauled
    0.73
    pull
    0.60
    ulage
    0.58
    Pull
    0.57
    carry
    0.57
    hauled
    0.56
    Activations Density 0.007%

    No Known Activations