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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8403
    Prev
    Next
    INDEX
    Explanations

    instances of optional parameters in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.45
     فرود
    -0.39
     nấu
    -0.38
    ̎
    -0.36
     مرد
    -0.36
    Alb
    -0.35
    他有
    -0.35
     course
    -0.35
     rythme
    -0.35
     Wach
    -0.34
    POSITIVE LOGITS
    findpost
    0.59
    (!__
    0.57
     Optional
    0.56
    KommentareTeilen
    0.56
    Optional
    0.55
    sizeCache
    0.52
     AssemblyCulture
    0.52
    nonatomic
    0.51
     мәкал
    0.51
    Erreferentziak
    0.50
    Activations Density 0.203%

    No Known Activations