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. 22-GEMMASCOPE-RES-16K
    6. 11379
    Prev
    Next
    INDEX
    Explanations

    references to links, identifiers, or structured data formats

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

    URLs and numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.59
    zeera
    -0.55
    ၅
    -0.48
    StackNavigator
    -0.47
     lenker
    -0.46
    ]^{-
    -0.45
    neither
    -0.45
    multer
    -0.45
    alny
    -0.44
    imanapun
    -0.43
    POSITIVE LOGITS
    Geplaatst
    0.70
    adpleegd
    0.60
    PerformLayout
    0.57
    例文帳に追加
    0.56
    قایناق‌لار
    0.54
     Obtén
    0.54
    Gweler
    0.53
     idiota
    0.53
     betweenstory
    0.53
     OMITTED
    0.52
    Activations Density 0.958%

    No Known Activations