© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 10124
    Prev
    Next
    INDEX
    Explanations

    specific medical and scientific terminology related to conditions and treatments

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

    comma followed by contrasting conjunction

    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
    bootstrapcdn
    -0.65
     defStyleAttr
    -0.40
    mybatisplus
    -0.39
    bufio
    -0.38
    noStroke
    -0.37
    adell
    -0.36
    THRESH
    -0.36
    的一声
    -0.35
    NamedQuery
    -0.35
    bcryptjs
    -0.35
    POSITIVE LOGITS
     while
    3.31
     whereas
    3.03
     mentre
    3.00
    while
    2.92
     tandis
    2.89
     mientras
    2.86
     sedangkan
    2.70
    whereas
    2.67
     enquanto
    2.66
     terwijl
    2.47
    Activations Density 1.006%

    No Known Activations