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

    Neuronpedia

    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. 13908
    Prev
    Next
    INDEX
    Explanations

    coding syntax elements related to functions and conditionals

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

    struct member access patterns using the arrow operator to access fields in C code.

    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
     faſt
    -0.50
     itſelf
    -0.49
     raiſ
    -0.49
     ſever
    -0.46
     ſtill
    -0.46
     Ausdrücke
    -0.45
     fufficient
    -0.45
     poffible
    -0.45
     quæ
    -0.44
     Grüsse
    -0.43
    POSITIVE LOGITS
     flags
    0.81
     Flags
    0.71
    flags
    0.66
    Flags
    0.60
     flag
    0.57
    riezmann
    0.54
     Flag
    0.52
     flagged
    0.51
     FLAG
    0.48
     Roskov
    0.48
    Activations Density 0.905%

    No Known Activations