© 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 - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8303
    Prev
    Next
    INDEX
    Explanations

    terms related to verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    divarius
    -0.87
    tagext
    -0.82
    iostream
    -0.78
     שוליים
    -0.77
    
    -0.76
     useStyles
    -0.76
    InjectMocks
    -0.75
    {}".
    -0.74
    mybatisplus
    -0.74
    férence
    -0.73
    POSITIVE LOGITS
     Ver
    1.27
     VER
    1.24
    Ver
    1.13
     ver
    1.13
     verm
    1.04
     verification
    1.03
     Verification
    1.02
     Verm
    1.02
    ver
    1.01
     Verme
    1.00
    Activations Density 0.140%

    No Known Activations