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. 22-GEMMASCOPE-RES-16K
    6. 12875
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols in a programming context

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

    Code, versions, and database names

    np_acts-logits-general · gemini-2.0-flash

    numbers ending sentences

    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
     désolés
    -0.68
    awarkan
    -0.53
     nume
    -0.53
     useSelector
    -0.50
    UBLIC
    -0.50
    ciptakan
    -0.49
     exc
    -0.48
    üe
    -0.47
    ratulations
    -0.47
    /*++
    -0.47
    POSITIVE LOGITS
    springframework
    1.12
    DoubleQuotes
    0.67
    
    0.66
     Baillargeon
    0.63
    AnchorTagHelper
    0.62
     Spring
    0.62
    ########.
    0.61
     spring
    0.60
     springs
    0.59
    bootstrapcdn
    0.59
    Activations Density 0.074%

    No Known Activations