© 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. 15739
    Prev
    Next
    INDEX
    Explanations

    elements of family dynamics and societal themes within narratives

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

    before numbers

    np_acts-logits-general · gemini-2.0-flash

    criminal organization

    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
     fumée
    -0.69
     समीक्षाओं
    -0.66
     tremp
    -0.66
     foncé
    -0.65
     Wikiseite
    -0.65
     démocr
    -0.65
     Wicidata
    -0.65
     jurí
    -0.65
     actifs
    -0.62
     conmigo
    -0.62
    POSITIVE LOGITS
     mysterious
    0.63
     mysteriously
    0.62
     titular
    0.60
     wealthy
    0.58
    insu
    0.56
     inexp
    0.55
    iress
    0.52
     discovers
    0.52
     obsessed
    0.51
     unwilling
    0.51
    Activations Density 0.449%

    No Known Activations