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. 9-GEMMASCOPE-RES-16K
    6. 1360
    Prev
    Next
    INDEX
    Explanations

    references to financial assessments and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тисти
    -0.48
     vasi
    -0.44
     Master
    -0.42
    master
    -0.42
    ):=\
    -0.41
     Record
    -0.41
     kepercayaan
    -0.41
     videre
    -0.41
    liesslich
    -0.41
    Master
    -0.41
    POSITIVE LOGITS
     שוליים
    0.67
     препратки
    0.62
     Autorizaciones
    0.62
     CanadaChoose
    0.60
     AssemblyProduct
    0.59
    VersionUID
    0.59
    TargetException
    0.58
    ynb
    0.58
     مرئيه
    0.58
     StatefulWidget
    0.58
    Activations Density 0.713%

    No Known Activations