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. 7019
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to medical and mental health conditions

    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
    RenderAtEndOf
    -0.59
    ftagPool
    -0.52
    PreExecute
    -0.49
     referenties
    -0.47
    ništvo
    -0.47
    AnchorStyles
    -0.45
    awtextra
    -0.44
    Aiheesta
    -0.42
    httphttps
    -0.42
     يتيمه
    -0.41
    POSITIVE LOGITS
     slowest
    0.52
     delaying
    0.50
    UrlResolution
    0.49
    shortest
    0.45
    最快
    0.45
    RuleContext
    0.44
     expedite
    0.43
    dela
    0.43
     delay
    0.42
    Delay
    0.42
    Activations Density 1.105%

    No Known Activations