© 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. 1456
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical diagnosis and research methodologies

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

    research activities and findings

    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
     famously
    -0.65
     iconic
    -0.57
     nuanced
    -0.49
     biodiversity
    -0.49
     showcasing
    -0.49
     showcased
    -0.48
     onboarding
    -0.47
     seamlessly
    -0.47
     stakeholders
    -0.47
     microbiome
    -0.47
    POSITIVE LOGITS
    faßt
    0.66
    bootstrapcdn
    0.60
     изпол
    0.57
    luß
    0.56
     Probleme
    0.55
    AnimationsModule
    0.54
     surla
    0.53
     mußten
    0.53
    harapkan
    0.52
     daß
    0.52
    Activations Density 0.144%

    No Known Activations