© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15329
    Prev
    Next
    INDEX
    Explanations

    structured data definitions and types in a programming context

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

    C preprocessor macro definitions and bitfield operations in header files.

    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
    Personendaten
    -0.73
     للاسماء
    -0.58
     Италијани
    -0.58
     kasarigan
    -0.56
    BeginContext
    -0.54
    hyrchwyd
    -0.52
    AccessFile
    -0.51
    ágenes
    -0.51
    stag
    -0.51
    Palmar
    -0.50
    POSITIVE LOGITS
     mask
    2.55
     masks
    2.39
     Mask
    2.20
    mask
    2.09
    Mask
    2.08
     Masks
    1.98
     MASK
    1.94
     masking
    1.90
     masked
    1.88
    Masks
    1.82
    Activations Density 0.342%

    No Known Activations