Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1455
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

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

    First initial followed by a period

    np_acts-logits-general · gemini-2.0-flash

    initial capital letter followed by a word

    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
     AssemblyCulture
    -0.78
    enumi
    -0.76
     alimentaires
    -0.69
    ]")]
    -0.65
     médicaux
    -0.61
     vectorielles
    -0.60
    rrggbb
    -0.60
     nationaux
    -0.59
    𓃵
    -0.56
     magnétique
    -0.56
    POSITIVE LOGITS
    PerformLayout
    0.73
     "..\..\..\
    0.60
     autorytatywna
    0.58
    ьаж
    0.57
    Hochspringen
    0.57
    ArgsConstructor
    0.56
     InputDecoration
    0.54
    S
    0.54
    O
    0.52
    日閲覧
    0.52
    Activations Density 0.193%

    No Known Activations