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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15855
    Prev
    Next
    INDEX
    Explanations

    references to characters and relationships in stories

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

    Japanese TV show Kyurangers

    np_acts-logits-general · gemini-2.0-flash

    Kyurangers characters and entities

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     diensten
    -0.32
    i
    -0.31
    r
    -0.31
     होने
    -0.31
    1
    -0.29
     goederen
    -0.29
    is
    -0.28
     appunto
    -0.28
    다는
    -0.28
     Dienste
    -0.28
    POSITIVE LOGITS
     Савезне
    0.82
    ftagPool
    0.73
     Italijani
    0.73
     Infórmanos
    0.72
    findpost
    0.71
    uxxxx
    0.71
    ➟
    0.70
    
    0.69
     TType
    0.69
    httphttps
    0.69
    Activations Density 0.263%

    No Known Activations