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. 23-GEMMASCOPE-RES-16K
    6. 6344
    Prev
    Next
    INDEX
    Explanations

    programming terms related to file handling and configuration in scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annica
    -0.61
    ourite
    -0.55
     
    -0.54
    RESUMO
    -0.48
    orithm
    -0.48
    ‍♂️
    -0.47
     all
    -0.46
    Ethylbenzene
    -0.46
    roduction
    -0.46
     a
    -0.46
    POSITIVE LOGITS
     autorytatywna
    1.01
     avoient
    0.90
     مرئيه
    0.78
     feroit
    0.77
     disambiguazione
    0.76
     utafitiHapana
    0.74
     argint
    0.74
     étoient
    0.74
     pouvoit
    0.73
     perſon
    0.72
    Activations Density 1.383%

    No Known Activations