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. 10-GEMMASCOPE-RES-16K
    6. 5661
    Prev
    Next
    INDEX
    Explanations

    conditional statements and definitions related to handling optional values in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.84
     /\.(
    -0.61
    extAlignment
    -0.61
    abestanden
    -0.61
    }{*}{
    -0.61
     autorytatywna
    -0.57
    InvalidProtocol
    -0.57
    +#+#
    -0.56
     veci
    -0.53
     matter
    -0.52
    POSITIVE LOGITS
    Nullable
    0.80
     يتيمه
    0.78
     kasarigan
    0.63
     vorhand
    0.62
     évent
    0.61
     nullable
    0.60
    InjectAttribute
    0.60
    ardians
    0.58
    berdayakan
    0.58
     HttpStatusCode
    0.57
    Activations Density 0.152%

    No Known Activations