© 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. 35-GEMMASCOPE-RES-16K
    11. 12598
    Prev
    Next
    INDEX
    Explanations

    the article "a" appearing in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zelfde
    -0.46
    :][
    -0.40
     oprot
    -0.38
    jenigen
    -0.36
    ressee
    -0.35
     صوتيه
    -0.35
    อะไร
    -0.35
     enough
    -0.34
     liknande
    -0.33
    rededor
    -0.33
    POSITIVE LOGITS
     result
    1.13
     consequence
    0.94
    result
    0.90
     matter
    0.82
     precaution
    0.79
    httphttps
    0.78
     prelude
    0.76
     conseguenza
    0.75
     RESULT
    0.73
     corollary
    0.73
    Activations Density 0.179%

    No Known Activations