© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 717
    Prev
    Next
    INDEX
    Explanations

    technical terms and function names related to programming and API specifications

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

    technical terms related to web technologies and structured data

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

    `request`, `modules`, `LayoutParams`, `options`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    LookAnd
    -0.93
    AsUp
    -0.79
     Shakspeare
    -0.79
    Personendaten
    -0.78
     Cæsar
    -0.77
     Anſ
    -0.76
     Reſ
    -0.76
     Monfieur
    -0.75
     Chriftian
    -0.74
    SharedCtor
    -0.74
    POSITIVE LOGITS
    ']))
    0.60
    ?>">
    0.60
    LabelTagHelper
    0.59
    '],
    0.57
    .],
    0.53
    '])
    0.53
    ']=$
    0.53
    viri
    0.52
    }$}
    0.50
    IALS
    0.50
    Activations Density 0.098%

    No Known Activations