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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 574
    Prev
    Next
    INDEX
    Explanations

    strings or identifiers within a technical context, particularly those associated with data fields or programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pembunuhan
    -0.43
    Vidite
    -0.43
    ̣ng
    -0.43
    Tazama
    -0.43
    éte
    -0.42
    Rohy
    -0.41
     cercle
    -0.40
    __["
    -0.39
    olism
    -0.39
    oredCriteria
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.97
    ')")
    0.83
     AssemblyProduct
    0.80
    PositiveButton
    0.80
     للاسماء
    0.80
    InputBorder
    0.79
    findpost
    0.78
    KURZBESCHREIBUNG
    0.78
    verwijspagina
    0.77
    })));
    0.77
    Activations Density 0.019%

    No Known Activations