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. 33-GEMMASCOPE-RES-131K
    6. 65786
    Prev
    Next
    INDEX
    Explanations

    references to military and geopolitical events involving the US

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suç
    -0.33
    system
    -0.30
    ucap
    -0.29
     Reforms
    -0.29
    outil
    -0.29
     Behörden
    -0.29
     débat
    -0.29
     reforms
    -0.29
     institutions
    -0.28
     querer
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.70
     protoimpl
    0.70
    ErrUnexpectedEOF
    0.66
    Vidite
    0.64
    SourceChecksum
    0.63
    DockStyle
    0.61
     utafitiHapana
    0.61
     Мексичка
    0.60
    +#+
    0.60
     surla
    0.59
    Activations Density 0.028%

    No Known Activations