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. 16-GEMMASCOPE-RES-16K
    6. 6737
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming language snippets

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

    Code-related punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code block structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.76
     Majefty
    -0.64
     Partagez
    -0.61
    aarrggbb
    -0.60
     CreateTagHelper
    -0.60
    LEncoder
    -0.58
    rscheinlichkeit
    -0.56
    さてさて
    -0.56
    Становништво
    -0.56
    esgue
    -0.56
    POSITIVE LOGITS
     nothing
    0.76
     ничего
    0.65
    ){}
    0.63
    (){}
    0.63
    </thead>
    0.61
     Nothing
    0.61
    Nothing
    0.60
    nothing
    0.59
     rien
    0.59
     NOTHING
    0.58
    Activations Density 0.147%

    No Known Activations