© 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. 21-GEMMASCOPE-RES-16K
    11. 2303
    Prev
    Next
    INDEX
    Explanations

    comparative expressions indicating a lesser degree or relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.62
     Anſ
    -0.62
     fuch
    -0.56
     ſever
    -0.56
     uchiha
    -0.55
     Meiji
    -0.55
    databind
    -0.53
     alſo
    -0.52
     Aline
    -0.52
     INA
    -0.52
    POSITIVE LOGITS
     they
    1.29
     usual
    1.19
     we
    1.06
    usual
    1.01
     ever
    1.01
     you
    0.97
     any
    0.96
     the
    0.95
    kyou
    0.88
     most
    0.86
    Activations Density 0.194%

    No Known Activations