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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3099
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those associated with scholarly work or works of art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    पया
    -0.71
    ijt
    -0.69
    ganj
    -0.67
     ISNI
    -0.65
    igon
    -0.64
    ')";
    -0.64
    rowse
    -0.64
    kier
    -0.63
     Marav
    -0.62
     Amic
    -0.62
    POSITIVE LOGITS
    RegressionTest
    0.67
    parsedMessage
    0.62
     particulières
    0.62
     turísticos
    0.62
     intégrée
    0.61
     sposa
    0.61
     conformément
    0.60
     âgées
    0.59
     aikaa
    0.58
     يتيمه
    0.56
    Activations Density 0.103%

    No Known Activations