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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105167
    Prev
    Next
    INDEX
    Explanations

    technical references related to software, user interaction, and programming specifics

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

    Tokens referring to key components, locations, or controllers within technical systems and digital environments.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انيف
    -0.52
     resourceCulture
    -0.52
    multer
    -0.50
    localVar
    -0.49
    AndEndTag
    -0.43
    ielsen
    -0.43
    $_['
    -0.42
    calipsis
    -0.41
    aspectj
    -0.40
     ब्रेकडाउन
    -0.40
    POSITIVE LOGITS
     chứ
    0.52
     rather
    0.51
    而不是
    0.50
     wikipagina
    0.49
    rather
    0.48
     surla
    0.46
     plutôt
    0.46
     kaynağından
    0.45
    而非
    0.44
     geométrico
    0.42
    Activations Density 0.208%

    No Known Activations