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. 2229
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and dollar signs

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

    Punctuation followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    punctuation and symbols

    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
    קישורים
    -0.95
     FontWeight
    -0.78
    Enllaces
    -0.72
    Ссылки
    -0.71
     AppCompat
    -0.70
     مشارکت‌کنندگان
    -0.70
    usermodel
    -0.68
     समीक्षाओं
    -0.65
     وتسجيلات
    -0.64
    VersionUID
    -0.61
    POSITIVE LOGITS
     }}$.
    1.08
    }.
    0.98
    ↵↵
    0.98
    ».
    0.96
    ').
    0.94
    \}$.
    0.93
    ™.
    0.92
    ()].
    0.92
    ®.
    0.91
    }}.
    0.91
    Activations Density 2.285%

    No Known Activations