© 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. 5852
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the term "new."

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

    new item or concept

    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
     hinweg
    -0.47
     이미
    -0.46
     defStyleAttr
    -0.44
    mbalikan
    -0.43
     dále
    -0.43
     already
    -0.42
     kemudian
    -0.41
     następnie
    -0.41
    already
    -0.40
     allerede
    -0.40
    POSITIVE LOGITS
    fang
    0.60
     additions
    0.59
    tonsoft
    0.56
    脚注の使い方
    0.55
     new
    0.53
     addition
    0.53
     arrivals
    0.52
     שוליים
    0.50
     kinds
    0.50
    sprint
    0.49
    Activations Density 0.042%

    No Known Activations