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. 24-GEMMASCOPE-RES-16K
    6. 16313
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their associated class attributes related to font-awesome icons

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

    HTML tags or code snippets

    np_acts-logits-general · gemini-2.0-flash

    icons and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.77
    UnsafeEnabled
    -0.71
    RenderAtEndOf
    -0.70
     @}
    -0.63
    IntoConstraints
    -0.63
     AspNetCore
    -0.63
     utafitiHapana
    -0.60
    awtextra
    -0.59
    asteroide
    -0.59
    lottes
    -0.58
    POSITIVE LOGITS
     fa
    0.91
    fa
    0.85
     FA
    0.59
    Fa
    0.57
     Fa
    0.56
    FA
    0.55
    idane
    0.49
    fas
    0.48
    ')}}">
    0.48
    ExecuteReader
    0.47
    Activations Density 0.119%

    No Known Activations