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. 11-GEMMASCOPE-RES-16K
    6. 7436
    Prev
    Next
    INDEX
    Explanations

    formatting elements related to mathematical notations or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.61
    posób
    -0.58
    FunctionFlags
    -0.58
     transfieras
    -0.57
    ={<
    -0.57
    digitalWrite
    -0.56
    amsmath
    -0.55
     ApiException
    -0.54
     iprot
    -0.53
    (&:
    -0.53
    POSITIVE LOGITS
     оригіналу
    0.68
     الاطلاع
    0.66
    </caption>
    0.64
     surla
    0.61
    SuppressLint
    0.57
    HtmlAttribute
    0.56
     nahilalakip
    0.56
    存于互联网档案馆
    0.56
     Tapatalk
    0.55
     consultato
    0.55
    Activations Density 0.151%

    No Known Activations