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

    Neuronpedia

    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. 16-GEMMASCOPE-RES-16K
    11. 3700
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts related to treatment and disorder evaluation

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

    Terms abbreviated with parentheses

    np_acts-logits-general · gemini-2.0-flash

    acronyms with abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nhiêu
    -0.40
     morreu
    -0.40
     presents
    -0.40
    }}}{\
    -0.39
     mostrarán
    -0.39
     kier
    -0.38
    pub
    -0.38
    stdc
    -0.38
     Randall
    -0.38
    ?
    -0.37
    POSITIVE LOGITS
    Geplaatst
    0.72
    oredCriteria
    0.67
    Życiorys
    0.64
     createSprite
    0.64
     DbType
    0.63
    tly
    0.60
     BoxFit
    0.60
     فريبيس
    0.59
    >{"
    0.59
    pholes
    0.59
    Activations Density 0.170%

    No Known Activations