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. 4471
    Prev
    Next
    INDEX
    Explanations

    XML or HTML-like tag structures in code snippets

    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
    BindingResult
    -0.60
     JADX
    -0.49
    LogFactory
    -0.48
     JSONArray
    -0.48
     Jurí
    -0.48
     AppDelegate
    -0.47
    corrhi
    -0.45
    WebRequest
    -0.45
     te
    -0.44
     Référence
    -0.44
    POSITIVE LOGITS
    WithIOException
    0.70
    Column
    0.67
     Column
    0.65
     Container
    0.65
    Row
    0.63
     disambiguazione
    0.62
     Row
    0.62
    Container
    0.62
    writeFieldEnd
    0.62
    ыгана
    0.60
    Activations Density 0.059%

    No Known Activations