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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15504
    Prev
    Next
    INDEX
    Explanations

    elements, fields, and data types in a structured format

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

    HTML or code snippets

    np_acts-logits-general · gemini-2.0-flash

    UnitOfMeasureReportingText

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.93
     pleaſure
    -0.91
     Monfieur
    -0.89
     Савезне
    -0.84
     Verſ
    -0.82
     myſelf
    -0.81
     Houſe
    -0.80
     itſelf
    -0.80
     Theſe
    -0.79
     Jefus
    -0.78
    POSITIVE LOGITS
     U
    0.62
     A
    0.52
     It
    0.50
     st
    0.50
     
    0.50
     No
    0.49
     u
    0.48
    GraphicsUnit
    0.48
     it
    0.47
     or
    0.47
    Activations Density 0.030%

    No Known Activations