© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10047
    Prev
    Next
    INDEX
    Explanations

    terms related to validation and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    міністра
    -0.50
    Referencie
    -0.49
     prins
    -0.47
    URLException
    -0.47
    rophoresis
    -0.47
    leos
    -0.45
     चल
    -0.45
    래스
    -0.44
     Ген
    -0.44
     Mar
    -0.44
    POSITIVE LOGITS
     verified
    1.57
    verified
    1.32
     verifying
    1.27
     Verified
    1.23
     verify
    1.23
     verifies
    1.19
    Verified
    1.15
     verification
    1.12
     Verification
    1.06
    Verifier
    0.94
    Activations Density 0.069%

    No Known Activations