Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15134
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to derivatives and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.81
    lobo
    -0.53
     torchvision
    -0.50
    WebServlet
    -0.50
    oros
    -0.49
    <bos>
    -0.49
     LUMP
    -0.49
    cVar
    -0.49
     getItemCount
    -0.49
    TryGetValue
    -0.48
    POSITIVE LOGITS
    Filmografia
    0.58
    exels
    0.58
    quitous
    0.55
    sticker
    0.54
     /\.
    0.54
     ErrIntOverflow
    0.53
    nodoc
    0.52
     BoxFit
    0.52
     Cinta
    0.50
     baga
    0.50
    Activations Density 0.473%

    No Known Activations