© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15922
    Prev
    Next
    INDEX
    Explanations

    warnings and advice related to safety and caution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.59
     realisation
    -0.53
     kasarigan
    -0.53
     correctly
    -0.52
    authentic
    -0.51
    ukone
    -0.49
    correctly
    -0.48
     realization
    -0.48
     understands
    -0.48
     calendriers
    -0.48
    POSITIVE LOGITS
     underestimate
    0.83
     relying
    0.74
     rely
    0.73
     Rely
    0.73
     trust
    0.70
     relied
    0.66
     allzu
    0.65
     complacency
    0.65
     blindly
    0.64
     hasty
    0.64
    Activations Density 0.294%

    No Known Activations