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. 24-GEMMASCOPE-RES-16K
    6. 4439
    Prev
    Next
    INDEX
    Explanations

    punctuation patterns and their context in sentences

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

    Text before a comma

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     -
    -0.65
     ,
    -0.64
     -,
    -0.62
     jedoch
    -0.60
     welcher
    -0.59
     Также
    -0.55
     somit
    -0.54
     также
    -0.54
    ;',
    -0.53
     —,
    -0.53
    POSITIVE LOGITS
     dammit
    0.81
    WriteBarrier
    0.77
     lest
    0.77
     jedenfalls
    0.73
     pronto
    0.73
     certainly
    0.71
     almeno
    0.71
    certainly
    0.69
    ">//
    0.68
    GraphicsUnit
    0.67
    Activations Density 0.357%

    No Known Activations