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. 96118
    Prev
    Next
    INDEX
    Explanations

    occurrences of the method "doInBackground" in asynchronous programming contexts

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

    designate/designates/designation

    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
    bootstrapcdn
    -0.42
     estrada
    -0.32
     esprits
    -0.30
     script
    -0.29
    チール
    -0.29
     uds
    -0.29
     binding
    -0.28
     khuẩn
    -0.28
    OMETRY
    -0.28
    ziału
    -0.28
    POSITIVE LOGITS
     Designated
    2.73
    Designated
    2.39
    designated
    1.77
     designated
    1.73
     designate
    1.41
     designating
    1.26
     Designation
    1.21
     designates
    1.18
     designations
    1.15
    Designation
    1.14
    Activations Density 0.000%

    No Known Activations