© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10128
    Prev
    Next
    INDEX
    Explanations

    references to historical traditions or cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.72
     CreateTagHelper
    -0.68
    lawayo
    -0.67
     Yarm
    -0.58
     ويكيپيديا
    -0.58
    Gambas
    -0.56
    sizePolicy
    -0.56
    autoIncrement
    -0.55
     Reykjavik
    -0.54
    LinkId
    -0.53
    POSITIVE LOGITS
     imperial
    0.59
     Imperial
    0.58
    Filmografie
    0.57
     court
    0.57
     tea
    0.53
     Tea
    0.53
     Scrolls
    0.52
    Imperial
    0.51
     Court
    0.51
     scholar
    0.50
    Activations Density 0.182%

    No Known Activations