Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12883
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and specifications

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

    Values with units (size, weight, etc.)

    np_acts-logits-general · gemini-2.0-flash

    units followed by descriptive nouns

    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
     كومونز
    -0.56
     Kome
    -0.54
    copg
    -0.54
     Decorations
    -0.53
     GetEnumerator
    -0.52
    omeness
    -0.52
     valign
    -0.52
    gbaar
    -0.50
     Archiproducts
    -0.50
     Fourteenth
    -0.48
    POSITIVE LOGITS
    Kaynakça
    0.66
    ″
    0.64
    TagMode
    0.64
     or
    0.63
    gypti
    0.60
    Personendaten
    0.57
    ′
    0.57
    Vidite
    0.54
     /\.(
    0.53
    pbs
    0.52
    Activations Density 0.736%

    No Known Activations