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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 475
    Prev
    Next
    INDEX
    Explanations

    attributes related to health conditions and their impact on patients

    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
    UnitTesting
    -0.63
    </caption>
    -0.58
    
    -0.51
    MetaType
    -0.49
     становника
    -0.47
    eip
    -0.44
    xnn
    -0.42
     onCancelled
    -0.41
    laan
    -0.41
    JsonFormat
    -0.41
    POSITIVE LOGITS
     left
    3.19
     Left
    2.65
    left
    2.54
    Left
    2.52
     LEFT
    2.46
     right
    2.34
    LEFT
    2.20
    左
    2.17
     Right
    2.07
    right
    2.01
    Activations Density 0.576%

    No Known Activations