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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1834
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.67
    脚注の使い方
    -0.65
     <<<<<<<<<<<<<<
    -0.63
    ArrowToggle
    -0.60
     تضيفلها
    -0.55
    Rohy
    -0.54
    ⓧ
    -0.53
    compromising
    -0.52
    +#+#
    -0.52
    ietf
    -0.51
    POSITIVE LOGITS
     وتسجيلات
    0.54
     simplifié
    0.50
    phosa
    0.47
    awtextra
    0.47
    MessageOf
    0.46
    =|
    0.46
    -|
    0.46
     podjet
    0.46
     jurado
    0.45
    página
    0.44
    Activations Density 0.464%

    No Known Activations