© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 7750
    Prev
    Next
    INDEX
    Explanations

    content related to specific names or designations, particularly in the context of organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    -1.01
    RegressionTest
    -1.00
    parsedMessage
    -0.97
    XMLSchema
    -0.95
    featureID
    -0.93
    jména
    -0.93
    PhysRev
    -0.93
    __':
    -0.93
    __':
    -0.91
    __":
    -0.91
    POSITIVE LOGITS
    flüs
    0.78
     McCar
    0.77
     szabály
    0.68
    lassung
    0.66
     
    0.65
    envie
    0.64
    stridium
    0.64
     Brescia
    0.63
    tobe
    0.63
     Blom
    0.62
    Activations Density 2.674%

    No Known Activations