© 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. 10-GEMMASCOPE-RES-16K
    11. 3389
    Prev
    Next
    INDEX
    Explanations

    file paths and related code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.55
    تمع
    -0.46
     sorte
    -0.44
    Variant
    -0.43
     manto
    -0.42
    ūros
    -0.41
     partes
    -0.41
    nee
    -0.40
     побу
    -0.40
    a
    -0.40
    POSITIVE LOGITS
    ViewImports
    4.72
    @[+][
    1.92
    WireFormatLite
    1.46
    AndEndTag
    1.37
     Roskov
    1.32
     BorderRadius
    1.27
    ContentAsync
    1.23
    AutoField
    1.14
     kasarigan
    1.08
    $_['
    1.00
    Activations Density 0.006%

    No Known Activations