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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15443
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and their histories, particularly focusing on symptoms and treatments

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

    followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    technical descriptions and specifications

    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
    NUMX
    -1.07
    enumi
    -0.83
    ScopeManager
    -0.82
     nemlig
    -0.81
     nämlich
    -0.80
     ainfi
    -0.77
    InjectAttribute
    -0.76
     justement
    -0.75
    AddTagHelper
    -0.74
    styleType
    -0.74
    POSITIVE LOGITS
     =
    0.84
     +
    0.74
     includes
    0.73
    :
    0.71
     same
    0.70
     &
    0.69
    ;
    0.67
     /
    0.63
     incl
    0.61
     -
    0.61
    Activations Density 0.941%

    No Known Activations