Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43412
    Prev
    Next
    INDEX
    Explanations

    variations in comparative phrases or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "between" in comparative or contrastive statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @jake
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.72
     purpoſe
    -0.71
     RSSSF
    -0.71
     houſe
    -0.70
     ſche
    -0.68
     neceff
    -0.68
     Waco
    -0.68
     sandero
    -0.67
     perſon
    -0.67
     Folly
    -0.66
    POSITIVE LOGITS
    between
    1.39
     between
    1.36
    BETWEEN
    1.35
     Between
    1.34
     BETWEEN
    1.30
    Between
    1.27
     betweenstory
    1.23
     zwischen
    1.20
    WebVitals
    1.19
     tussen
    1.16
    Activations Density 0.062%

    No Known Activations