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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16352
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and its impact on patients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zug
    -0.51
    adaptiveStyles
    -0.43
     ver
    -0.40
     gran
    -0.37
     cab
    -0.35
    TRIBUN
    -0.35
    Zug
    -0.35
    arraycopy
    -0.34
    CGFloat
    -0.34
     напо
    -0.34
    POSITIVE LOGITS
    ftagPool
    0.63
    OGND
    0.60
    enumii
    0.56
    WaitGroup
    0.54
     بيها
    0.51
    SBATCH
    0.50
    tamo
    0.48
     bailarina
    0.47
    localctx
    0.46
    ckså
    0.45
    Activations Density 0.078%

    No Known Activations