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. 21-GEMMASCOPE-RES-16K
    6. 6797
    Prev
    Next
    INDEX
    Explanations

    elements of Japanese and Chinese language content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sœurs
    -0.53
     frères
    -0.47
     religieuses
    -0.46
     reales
    -0.44
     noires
    -0.44
     datter
    -0.44
     venner
    -0.43
     fratelli
    -0.43
     generales
    -0.42
     sure
    -0.41
    POSITIVE LOGITS
    EndGlobalSection
    0.88
    LookAnd
    0.80
     autorytatywna
    0.80
     Мексичка
    0.78
     AssemblyCulture
    0.77
    IndentedString
    0.77
    matchCondition
    0.76
    principalColumn
    0.76
     Roskov
    0.74
    #+#
    0.72
    Activations Density 0.061%

    No Known Activations