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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 118
    Prev
    Next
    INDEX
    Explanations

    structured data elements, specifically related to categories and groups

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

    technical documentation language related to computational systems, scientific research methodologies, and structured data descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    antiation
    -0.39
     للاسماء
    -0.36
    LITERAL
    -0.36
    Rüyada
    -0.36
    PullParser
    -0.35
    ेशा
    -0.35
     Vi
    -0.35
    ReusableCell
    -0.35
    ResourceId
    -0.34
    findpost
    -0.32
    POSITIVE LOGITS
     groupings
    0.66
     clusters
    0.60
     groups
    0.58
     betweenstory
    0.58
    SequentialGroup
    0.55
     grouping
    0.54
     AssemblyTitle
    0.52
     gruppi
    0.51
     accumulations
    0.49
     grupper
    0.48
    Activations Density 0.694%

    No Known Activations