© 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. 0-GEMMASCOPE-RES-16K
    11. 12660
    Prev
    Next
    INDEX
    Explanations

    references to products or commodities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.94
    BeginContext
    -0.77
    tagHelperRunner
    -0.76
    AndEndTag
    -0.74
    دانشنامهٔ
    -0.72
    URIComponent
    -0.69
    endphp
    -0.69
    PyTuple
    -0.68
     apologised
    -0.67
    FieldBuilder
    -0.66
    POSITIVE LOGITS
     happily
    0.63
     mijne
    0.63
     présidenti
    0.60
     démocr
    0.60
     rédaction
    0.59
     normaux
    0.58
     chré
    0.58
     vérit
    0.56
     stabilité
    0.55
     bonté
    0.55
    Activations Density 0.132%

    No Known Activations