© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6486
    Prev
    Next
    INDEX
    Explanations

    punctuations and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RuleContext
    -0.55
     Corsa
    -0.54
     Pacer
    -0.54
    ManagedBean
    -0.50
     PPS
    -0.50
     Cors
    -0.50
     Rasa
    -0.50
     Technician
    -0.50
     IPC
    -0.50
     Carrera
    -0.49
    POSITIVE LOGITS
     oftentimes
    0.46
     كومونز
    0.43
     resourceCulture
    0.43
     it
    0.43
    eramente
    0.39
     orejas
    0.39
    出版年
    0.38
    úgó
    0.38
     genellikle
    0.38
    sometimes
    0.38
    Activations Density 0.707%

    No Known Activations