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. 21-GEMMASCOPE-RES-16K
    6. 11363
    Prev
    Next
    INDEX
    Explanations

    references to systemic health issues and their implications on individual well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    放題
    -0.47
    Progression
    -0.42
    OGND
    -0.42
     Reden
    -0.41
    PTION
    -0.41
     Vorm
    -0.41
    AKS
    -0.40
    SerializedSize
    -0.40
    spection
    -0.39
     disponibilités
    -0.39
    POSITIVE LOGITS
     permanent
    0.72
     permanently
    0.69
     forever
    0.62
    permanent
    0.62
     lasting
    0.62
     PERMAN
    0.60
     Permanent
    0.57
     perman
    0.56
    Permanent
    0.56
     legacies
    0.55
    Activations Density 0.556%

    No Known Activations