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. 22-GEMMASCOPE-RES-16K
    6. 7894
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and expressions

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

    Programming symbols

    np_acts-logits-general · gemini-2.0-flash

    @>>>

    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
     
    -0.51
    ')):
    -0.50
     BoxDecoration
    -0.49
    ________________
    -0.48
    ")),
    -0.46
     ________
    -0.46
    ")){
    -0.46
    .*")]
    -0.45
    ']):
    -0.43
    例文帳に追加
    -0.43
    POSITIVE LOGITS
    =\
    0.82
    =(
    0.77
    =>
    0.77
    !=
    0.70
    ==
    0.69
    =,
    0.69
    =&
    0.68
    thâu
    0.68
    >
    
    0.67
    =.
    0.67
    Activations Density 0.804%

    No Known Activations