© 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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11604
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly related to function structures and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.36
     also
    -0.34
     subsequent
    -0.32
     POP
    -0.29
     further
    -0.29
     additional
    -0.29
     instead
    -0.28
    then
    -0.28
     for
    -0.28
     repair
    -0.28
    POSITIVE LOGITS
    GTCX
    0.93
     Италијани
    0.81
    WithIOException
    0.79
    Diweddarwch
    0.75
     Italijanski
    0.73
    RectangleBorder
    0.73
    RotationOrder
    0.72
     Normdatei
    0.71
     nargin
    0.68
    ReusableCell
    0.67
    Activations Density 0.211%

    No Known Activations