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. 1-GEMMASCOPE-RES-16K
    6. 13490
    Prev
    Next
    INDEX
    Explanations

    references to counties and associated names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.65
    WithIOException
    -0.64
    featureID
    -0.63
    shirt
    -0.61
     الحره
    -0.59
     وتسجيلات
    -0.58
    存于互联网档案馆
    -0.58
    脚注の使い方
    -0.56
    shirts
    -0.56
    cheinend
    -0.56
    POSITIVE LOGITS
     county
    2.12
    county
    1.85
     County
    1.74
    County
    1.73
     COUNTY
    1.69
     counties
    1.51
    COUNTY
    1.48
     Counties
    1.18
     parish
    0.95
    县
    0.90
    Activations Density 0.164%

    No Known Activations