© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9575
    Prev
    Next
    INDEX
    Explanations

    references to streams, particularly in a technical or programming context

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

    the word "stream" appearing in technical or programming contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.51
    ftagPool
    -0.41
    IContainer
    -0.41
    UnitTesting
    -0.39
     فريبيس
    -0.35
    adaptiveStyles
    -0.35
    rizona
    -0.35
    libft
    -0.34
     puissiez
    -0.34
     OnInit
    -0.33
    POSITIVE LOGITS
     Stream
    0.96
     STREAM
    0.90
    Stream
    0.82
     stream
    0.81
    stream
    0.73
    流
    0.73
     Streams
    0.72
     streams
    0.69
    estream
    0.69
     流
    0.69
    Activations Density 0.137%

    No Known Activations