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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3952
    Prev
    Next
    INDEX
    Explanations

    references to leather and synthetic materials

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

    Leather or synthetic material

    np_acts-logits-general · gemini-2.0-flash

    leather and associated goods

    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
    帖最后由
    -0.78
    tvguidetime
    -0.75
     ujednoznacz
    -0.68
     Meksiku
    -0.64
     propOrder
    -0.58
    tagHelperRunner
    -0.57
    retudo
    -0.56
    WebElementEntity
    -0.56
     kasarigan
    -0.56
    Hochspringen
    -0.56
    POSITIVE LOGITS
    製の
    0.70
    製
    0.58
    covered
    0.56
    versiti
    0.55
     material
    0.55
    制品
    0.52
     covered
    0.51
     lined
    0.51
     lining
    0.50
    work
    0.50
    Activations Density 0.469%

    No Known Activations