© 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. 38-GEMMASCOPE-RES-16K
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    components related to mathematical or logical operations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     financière
    -0.73
     fibrosis
    -0.73
     fluorescence
    -0.72
     fattori
    -0.71
     filmed
    -0.71
     factored
    -0.70
     firmware
    -0.69
     funeral
    -0.69
     frequency
    -0.69
     fucking
    -0.69
    POSITIVE LOGITS
     abbraccio
    0.45
    ismet
    0.42
    uestamente
    0.40
    baomidou
    0.38
     možno
    0.37
    ArgsConstructor
    0.36
    Abraços
    0.36
    IsUnicode
    0.36
    copg
    0.35
     Normdatei
    0.34
    Activations Density 1.413%

    No Known Activations