© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38548
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements and monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -1.02
    IsContent
    -0.88
    parsedMessage
    -0.84
     ddelweddau
    -0.82
    UserScript
    -0.80
     Roskov
    -0.80
    windowFixed
    -0.79
     Efq
    -0.79
    ]');
    -0.77
    MLLoader
    -0.77
    POSITIVE LOGITS
     тоже
    0.69
     also
    0.69
     too
    0.63
    also
    0.61
     نیز
    0.60
     ebenfalls
    0.60
     également
    0.59
     tamén
    0.57
     também
    0.57
    Also
    0.54
    Activations Density 0.348%

    No Known Activations