© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    the presence of the document's structural markers or special tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clearfix
    -0.64
    RUB
    -0.61
     pathlib
    -0.61
    stoy
    -0.61
     Monfieur
    -0.58
    fclose
    -0.58
     tonel
    -0.58
     NEO
    -0.56
    anguera
    -0.55
     ValueError
    -0.55
    POSITIVE LOGITS
    例文帳に追加
    0.88
     CreateTagHelper
    0.86
    __);
    0.83
    </tr>
    0.80
     الحره
    0.78
    исленность
    0.74
    енча
    0.73
    PerformLayout
    0.72
    __))
    0.69
    ↵
    0.68
    Activations Density 0.031%

    No Known Activations