Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9111
    Prev
    Next
    INDEX
    Explanations

    issues related to connections, performance, and maintenance in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.72
    styleType
    -0.70
    RenderAtEndOf
    -0.70
    AddHtmlAttribute
    -0.67
     فريبيس
    -0.67
    UnusedPrivate
    -0.66
     ostavi
    -0.66
    Clubs
    -0.65
    IsMutable
    -0.64
    揄
    -0.62
    POSITIVE LOGITS
     company
    1.01
     church
    0.83
     festival
    0.81
    company
    0.81
     clinic
    0.80
     museum
    0.79
     program
    0.78
     restaurant
    0.78
     system
    0.78
     project
    0.77
    Activations Density 1.282%

    No Known Activations