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. 43414
    Prev
    Next
    INDEX
    Explanations

    molecular structures and their chemical compositions

    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
     وتسجيلات
    -0.98
    ChildScrollView
    -0.88
     ſche
    -0.87
     Cæsar
    -0.86
    er
    -0.84
     Negroes
    -0.84
     DPM
    -0.84
     Wilber
    -0.83
     Jefus
    -0.82
    erdo
    -0.81
    POSITIVE LOGITS
    th
    1.25
    ath
    1.24
    uth
    1.23
    ATH
    1.20
    TH
    1.18
     TH
    1.11
    lith
    1.07
     Muth
    1.07
    ith
    1.04
     ATH
    1.02
    Activations Density 0.088%

    No Known Activations