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. 7347
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to financial performance

    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
     برانيه
    -0.48
    帖最后由
    -0.47
    nodoc
    -0.46
    Cartney
    -0.43
    enment
    -0.43
    dersfield
    -0.42
    transQ
    -0.42
    ndata
    -0.41
     المعيارى
    -0.41
    \|_{\
    -0.40
    POSITIVE LOGITS
     will
    0.91
     hopefully
    0.79
    hopefully
    0.74
    可能會
    0.68
    Hopefully
    0.68
     Hopefully
    0.68
    likely
    0.65
     provavelmente
    0.65
     possibly
    0.65
     likely
    0.65
    Activations Density 0.812%

    No Known Activations