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. 21-GEMMASCOPE-RES-16K
    6. 8570
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to food insecurity and health-related assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.60
    fated
    -0.58
     Wikimedijinoj
    -0.56
     EconPapers
    -0.56
     stratigraphy
    -0.55
     centralization
    -0.52
    ctron
    -0.51
    assertArray
    -0.49
     phylogeny
    -0.49
    posited
    -0.49
    POSITIVE LOGITS
     moderate
    1.42
     moderately
    1.29
     medium
    1.21
     Moderate
    1.15
     Moderately
    1.08
    medium
    1.08
    moderate
    1.07
    Moderate
    1.06
     Medium
    1.03
     intermediate
    1.01
    Activations Density 0.981%

    No Known Activations