© 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. 22-GEMMASCOPE-RES-16K
    11. 13613
    Prev
    Next
    INDEX
    Explanations

    tokens indicating the presence of a special character in the text

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

    Punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by various words

    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
    原始内容存档于
    -0.85
    AccessorTable
    -0.79
     ?>/
    -0.77
     CreateTagHelper
    -0.74
    '>
    -0.74
    %)$
    -0.73
    )");
    -0.70
    HostException
    -0.70
    %");
    -0.70
    +#+#
    -0.69
    POSITIVE LOGITS
    ‍
    0.70
    ⎈
    0.56
    ‌‌
    0.49
    xFFFF
    0.48
    argout
    0.48
     مفص
    0.47
    <strong>
    0.47
    .__
    0.47
    ®
    0.47
    が発
    0.46
    Activations Density 0.059%

    No Known Activations