© 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. 41-GEMMASCOPE-RES-16K
    6. 7559
    Prev
    Next
    INDEX
    Explanations

    terms related to programming errors and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrived
    -0.65
     acted
    -0.62
     erfolgt
    -0.60
     remain
    -0.59
     arrive
    -0.57
     arrives
    -0.57
     проводится
    -0.57
     vznik
    -0.57
     exist
    -0.56
     occur
    -0.56
    POSITIVE LOGITS
     ammi
    0.32
     *)__
    0.32
     tegens
    0.31
     stadio
    0.30
     लेकर
    0.30
     ople
    0.30
     vastaan
    0.30
    quiao
    0.29
    ől
    0.29
    とする
    0.29
    Activations Density 0.101%

    No Known Activations