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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 8413
    Prev
    Next
    INDEX
    Explanations

    terms related to programming operations and processes, particularly those involving data loading and saving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.67
     Audiodateien
    -0.43
    SerializedName
    -0.42
    alleye
    -0.42
    ̙
    -0.41
     QtCore
    -0.41
    ArgsConstructor
    -0.41
     समीक्षक
    -0.39
    crollView
    -0.38
    sprodu
    -0.37
    POSITIVE LOGITS
    AndSet
    0.78
     existing
    0.77
    新的
    0.75
    Existing
    0.72
     Existing
    0.71
     Theſe
    0.71
     new
    0.71
    单个
    0.70
     EXISTING
    0.69
     ulang
    0.68
    Activations Density 0.308%

    No Known Activations