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. 709
    Prev
    Next
    INDEX
    Explanations

    opening and closing curly braces indicating block structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mybatisplus
    -0.74
    findpost
    -0.73
    NewUrlParser
    -0.72
     '\\;'
    -0.71
     lenker
    -0.70
    yntaxException
    -0.68
    ChildScrollView
    -0.66
    Filmografie
    -0.66
    Enllaces
    -0.66
     maxn
    -0.66
    POSITIVE LOGITS
     nothing
    0.87
    nothing
    0.84
    Nothing
    0.80
     Nothing
    0.77
    NOTHING
    0.76
     NOTHING
    0.75
    anything
    0.72
    </tbody>
    0.69
     anything
    0.67
     nothin
    0.64
    Activations Density 0.035%

    No Known Activations