© 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. 15952
    Prev
    Next
    INDEX
    Explanations

    references to data, studies, or citations in academic writing

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

    Refers to other research papers via bracketed numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers in brackets

    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
    GEBURTSDATUM
    -0.77
    )}</
    -0.71
    XmlAccessorType
    -0.69
    ditto
    -0.66
    +#+
    -0.66
    mybatisplus
    -0.66
    SBATCH
    -0.63
    posedge
    -0.63
    SequentialGroup
    -0.63
    帖最后由
    -0.63
    POSITIVE LOGITS
     producteurs
    0.49
     pédagogique
    0.47
     Paglinawan
    0.45
     blessés
    0.42
     deschis
    0.40
     fournisseurs
    0.40
    ducers
    0.40
    dores
    0.39
     أمريكي
    0.39
     tecnico
    0.39
    Activations Density 0.713%

    No Known Activations