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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1760
    Prev
    Next
    INDEX
    Explanations

    code file types and their related extensions

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

    File paths with code file extensions

    np_acts-logits-general · gemini-2.0-flash

    programming language identifiers

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    _));
    -0.76
    WebElementEntity
    -0.74
    endswith
    -0.69
    setof
    -0.60
     समीक्षाओं
    -0.59
    ValueStyle
    -0.58
    ()));
    
    -0.58
    }))
    
    -0.56
    WriteTagHelper
    -0.55
    })$}
    -0.55
    POSITIVE LOGITS
    таратура
    0.58
    Ranks
    0.57
     Obrador
    0.56
     atheism
    0.54
    Unavailable
    0.54
     ligiloj
    0.54
    issau
    0.53
     Armies
    0.52
     poffible
    0.51
     rând
    0.51
    Activations Density 0.212%

    No Known Activations