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. 16-GEMMASCOPE-RES-16K
    6. 375
    Prev
    Next
    INDEX
    Explanations

    elements related to structure and formatting in writing, particularly in code or procedural text

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

    Follows "the", "a", or "an" and is a number

    np_acts-logits-general · gemini-2.0-flash

    extra, the first, the next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essoas
    -0.53
    ImageContext
    -0.49
    makeText
    -0.47
    localctx
    -0.45
     viewDid
    -0.45
     yonder
    -0.43
     perfons
    -0.43
     interests
    -0.42
    RenderAtEndOf
    -0.41
    endphp
    -0.41
    POSITIVE LOGITS
     extra
    0.62
    Aspect
    0.61
    脚注の使い方
    0.60
     ADDITIONAL
    0.58
     allAfrica
    0.57
    aspect
    0.56
    تقاوى
    0.55
    extra
    0.55
     ostavi
    0.55
     aspect
    0.54
    Activations Density 0.330%

    No Known Activations