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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13353
    Prev
    Next
    INDEX
    Explanations

    references to specific materials and ingredients, particularly in culinary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.20
     Efq
    -1.16
     myſelf
    -1.14
     Jefus
    -1.03
     itſelf
    -1.03
     purpoſe
    -1.02
    oplayer
    -0.98
     raiſ
    -0.96
     ſeveral
    -0.96
     Anſ
    -0.95
    POSITIVE LOGITS
    n
    0.65
     Spez
    0.64
     im
    0.64
    ampton
    0.63
     Cris
    0.62
     IM
    0.62
    ↵
    0.62
    t
    0.61
    h
    0.59
    amide
    0.59
    Activations Density 0.969%

    No Known Activations