Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129863
    Prev
    Next
    INDEX
    Explanations

    biological interactions and signaling pathways related to viral infections

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

    nuclear translocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.47
    Cyfeiriadau
    -0.38
     libéral
    -0.36
    InOrder
    -0.36
    Izvori
    -0.35
    뀔
    -0.35
    PRNewswire
    -0.34
    KindOfClass
    -0.34
    ArgsConstructor
    -0.34
     gentile
    -0.34
    POSITIVE LOGITS
     localization
    0.75
     relocating
    0.69
     relocate
    0.68
     translocation
    0.68
     localisation
    0.66
     trafficking
    0.66
     redistribution
    0.65
     localización
    0.65
     redistribute
    0.65
     relocated
    0.65
    Activations Density 0.526%

    No Known Activations