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. 15419
    Prev
    Next
    INDEX
    Explanations

    elements related to correspondence, formal letters, and collective communication

    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
    tagHelperRunner
    -0.96
     BrowserModule
    -0.74
    ItemBackground
    -0.73
     CommonModule
    -0.70
    BrowserModule
    -0.69
    yarnpkg
    -0.65
     Italijanski
    -0.64
    WebElementEntity
    -0.63
     SafeMath
    -0.63
    ennies
    -0.62
    POSITIVE LOGITS
    Vezi
    0.49
    宛
    0.48
     destinées
    0.44
     regionales
    0.43
    verständlich
    0.43
    に向けて
    0.43
     perguntas
    0.42
    quillas
    0.42
     devaient
    0.42
    Tembelea
    0.41
    Activations Density 0.281%

    No Known Activations