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. 13661
    Prev
    Next
    INDEX
    Explanations

    references to familial or parental relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    而非
    -0.56
     post
    -0.54
     lediglich
    -0.53
     literally
    -0.52
    wtf
    -0.51
    toir
    -0.50
    氏の
    -0.50
     essentially
    -0.50
    #+#
    -0.49
    に関しては
    -0.48
    POSITIVE LOGITS
     faſt
    0.94
     Jefus
    0.93
     ſeveral
    0.88
     preſent
    0.84
     Majefty
    0.84
     greateſt
    0.82
     poffible
    0.81
     purpoſe
    0.80
     reaſon
    0.79
     myſelf
    0.79
    Activations Density 0.116%

    No Known Activations