© 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. 28-GEMMASCOPE-RES-16K
    11. 3967
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data handling and buffer operations

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

    Deals with bytes, buffers, and data chunks

    np_acts-logits-general · gemini-2.0-flash

    writing buffer data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ger
    -0.34
     Ger
    -0.32
     pop
    -0.31
     reg
    -0.31
     Ray
    -0.31
     Maha
    -0.31
     UIS
    -0.29
     scala
    -0.29
     licenses
    -0.29
     Ann
    -0.29
    POSITIVE LOGITS
     Bytes
    0.79
    ChildScrollView
    0.76
     bytes
    0.73
    bytes
    0.73
     buffer
    0.72
     ProtoMessage
    0.71
     chunks
    0.71
    BufferException
    0.69
     chunk
    0.68
     BytesLike
    0.67
    Activations Density 1.029%

    No Known Activations