Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13168
    Prev
    Next
    INDEX
    Explanations

    descriptions of adhesive products or methods of using them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.70
     Administrativna
    -0.69
     AssemblyProduct
    -0.69
     Paglinawan
    -0.67
    WebVitals
    -0.66
     ErrIntOverflow
    -0.64
     fight
    -0.63
     indisponible
    -0.63
    новниш
    -0.63
     diph
    -0.62
    POSITIVE LOGITS
     adhesive
    1.00
     Adhesive
    0.92
     adhesives
    0.80
    adhesive
    0.76
     sticky
    0.75
    Sticky
    0.67
     adhesivo
    0.65
    sticky
    0.64
     Sticky
    0.63
     adhe
    0.61
    Activations Density 0.204%

    No Known Activations