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. 4297
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structural components 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
     كومونز
    -0.84
     Савезне
    -0.80
    oredCriteria
    -0.74
     podjela
    -0.73
    AsUp
    -0.71
    rrggbb
    -0.70
     Bioaccumulative
    -0.70
     ErrIntOverflow
    -0.69
    TypedDataSet
    -0.68
    RenderAtEndOf
    -0.67
    POSITIVE LOGITS
    ↵
    1.26
    ↵↵
    0.65
    0.64
    </h4>
    0.57
    </h2>
    0.56
    DockStyle
    0.52
    。
    0.51
    })();
    0.49
    </h1>
    0.49
     defaultstate
    0.48
    Activations Density 0.277%

    No Known Activations