© 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. 18-GEMMASCOPE-RES-16K
    11. 408
    Prev
    Next
    INDEX
    Explanations

    elements related to healthcare and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    moderation or mitigation

    np_acts-logits-general · gemini-2.0-flash

    moderately positive evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unbelievably
    -0.75
     unbelievable
    -0.67
     unglaub
    -0.66
     unimaginable
    -0.66
    CascadeType
    -0.66
     incredible
    -0.64
     supremely
    -0.63
    atissimo
    -0.63
     enormous
    -0.62
     irresistible
    -0.62
    POSITIVE LOGITS
     decent
    1.13
     moderately
    1.09
     somewhat
    1.07
     fairly
    1.04
     Fairly
    1.03
    Decent
    1.01
     decently
    0.99
     reasonably
    0.99
     Decent
    0.97
     relatively
    0.94
    Activations Density 0.402%

    No Known Activations