Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14746
    Prev
    Next
    INDEX
    Explanations

    mentions of computational processes and context in time-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roppo
    -0.65
    webElement
    -0.61
     معه
    -0.61
    camente
    -0.61
    riki
    -0.60
    mäßig
    -0.60
    Schedulers
    -0.59
     légales
    -0.59
    хьтан
    -0.59
    olith
    -0.59
    POSITIVE LOGITS
     which
    0.77
     why
    0.77
     how
    0.76
    ณะ
    0.74
     coloro
    0.71
     whose
    0.69
     Tym
    0.69
     indem
    0.68
     inasmuch
    0.68
     where
    0.67
    Activations Density 0.287%

    No Known Activations