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. 35-GEMMASCOPE-RES-16K
    6. 7358
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those related to file input/output and JSON processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jadx
    -0.44
     épaules
    -0.44
     przet
    -0.42
    Spread
    -0.40
    MethodManager
    -0.39
     Jenderal
    -0.39
     Spreading
    -0.38
    énération
    -0.38
    spread
    -0.38
     Eigent
    -0.38
    POSITIVE LOGITS
     streams
    1.59
     stream
    1.59
     Stream
    1.41
     Streams
    1.36
     STREAM
    1.31
    stream
    1.30
    Stream
    1.26
    streams
    1.25
    Streams
    1.21
    STREAM
    1.12
    Activations Density 0.552%

    No Known Activations