© 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. 15-GEMMASCOPE-RES-16K
    11. 3043
    Prev
    Next
    INDEX
    Explanations

    tokens or symbols associated with numerical or legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -1.01
    sizeCache
    -0.96
    featureID
    -0.93
    зулта
    -0.92
     насељу
    -0.91
    Tikang
    -0.86
    Референце
    -0.86
    ChildScrollView
    -0.84
    الحياه
    -0.83
    Хьажоргаш
    -0.82
    POSITIVE LOGITS
     فريبيس
    0.52
    [toxicity=0]
    0.48
    <strong>
    0.45
    例文帳に追加
    0.44
    </blockquote>
    0.44
    徊
    0.40
    </h5>
    0.39
    </h4>
    0.38
    請繼續往下閱讀
    0.38
    ↵
    0.37
    Activations Density 0.913%

    No Known Activations