© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73905
    Prev
    Next
    INDEX
    Explanations

    references to streaming data or streams in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stream cipher, socket, stream, lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coder
    -0.53
     Pity
    -0.53
     esquerdo
    -0.51
    pity
    -0.50
     boron
    -0.49
     femininos
    -0.48
     Niki
    -0.48
     Donnie
    -0.47
     getLogin
    -0.47
    <h4>
    -0.46
    POSITIVE LOGITS
     stream
    1.27
     STREAM
    1.26
    Stream
    1.26
     Stream
    1.23
    stream
    1.23
    estream
    1.05
     streams
    0.98
     Streams
    0.96
    STREAM
    0.94
    Streams
    0.86
    Activations Density 0.010%

    No Known Activations