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. 13522
    Prev
    Next
    INDEX
    Explanations

    terms related to risk factors and health conditions

    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
     CURIAM
    -0.60
    TypedDataSet
    -0.57
     <<<<<<<<<<<<<<
    -0.54
    ніципалі
    -0.53
    AndPassword
    -0.52
    PerformLayout
    -0.51
     חיצוניים
    -0.51
    WithIOException
    -0.48
    γραφή
    -0.47
    IContainer
    -0.47
    POSITIVE LOGITS
     risk
    3.46
     risks
    3.01
    risk
    2.93
     Risk
    2.88
    Risk
    2.75
     RISK
    2.70
    risks
    2.46
     Risks
    2.45
    RISK
    2.43
     risked
    2.41
    Activations Density 0.445%

    No Known Activations