© 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 EvalsExportsinterp-engineNEWAPI 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. 10802
    Prev
    Next
    INDEX
    Explanations

    terms associated with adverse health effects and medical conditions

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

    a shift, change, or opposite

    np_acts-logits-general · gemini-2.0-flash

    contrary outcomes or negations

    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
    IsContent
    -0.68
    脚注の使い方
    -0.58
     '\\;'
    -0.53
    EXTERN
    -0.50
    clickable
    -0.48
    importanza
    -0.47
     dám
    -0.47
    asiun
    -0.47
     différence
    -0.47
    withIdentifier
    -0.47
    POSITIVE LOGITS
     malah
    1.27
     justru
    1.23
    反而
    1.21
    むしろ
    1.08
    かえ
    1.00
     anzi
    0.97
     worsen
    0.91
     наоборот
    0.89
    逆に
    0.89
     instead
    0.85
    Activations Density 0.379%

    No Known Activations