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. 22-GEMMASCOPE-RES-16K
    6. 14046
    Prev
    Next
    INDEX
    Explanations

    baseball player statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LayoutStyle
    -0.54
    amment
    -0.50
    RetentionPolicy
    -0.50
    adamente
    -0.49
     canst
    -0.49
    ficulty
    -0.49
     userDetails
    -0.48
    ngOn
    -0.47
    araj
    -0.47
    NewGuid
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیا
    0.80
     extend
    0.76
    BeginContext
    0.74
     extending
    0.71
     Extend
    0.64
     extends
    0.62
    enumii
    0.62
     move
    0.62
     tartalomajánló
    0.62
     moving
    0.62
    Activations Density 0.149%

    No Known Activations