© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 111337
    Prev
    Next
    INDEX
    Explanations

    occurrences of descriptors related to roles and responsibilities in a context, particularly in relation to performance and classification

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

    respectively or listed items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    itself
    -0.60
     itself
    -0.59
    󠁢
    -0.59
     zowel
    -0.55
    无论是
    -0.55
    不管是
    -0.50
     zarówno
    -0.50
     eikä
    -0.49
    both
    -0.49
    了一个
    -0.49
    POSITIVE LOGITS
     respectively
    1.25
     respectivamente
    1.12
    respectively
    1.03
     respectivement
    0.95
     respective
    0.88
    それぞれ
    0.72
     examples
    0.70
     among
    0.66
     etc
    0.65
     соответственно
    0.65
    Activations Density 0.277%

    No Known Activations