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. 10-GEMMASCOPE-RES-16K
    6. 13384
    Prev
    Next
    INDEX
    Explanations

    sources or references to authors and critics in the context of reviews or discussions about media

    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
    -0.90
    rungsseite
    -0.87
    AnchorStyles
    -0.85
     saites
    -0.75
     createSprite
    -0.72
    xaml
    -0.69
    帖最后由
    -0.67
     cliquez
    -0.63
    tonsoft
    -0.63
     informée
    -0.62
    POSITIVE LOGITS
    VersionUID
    0.50
     kasarigan
    0.48
    tifier
    0.48
    водство
    0.45
    ειτουργ
    0.44
     hypertrophy
    0.43
     ؛
    0.43
    Hentet
    0.42
    <>();
    0.42
    tifies
    0.41
    Activations Density 0.562%

    No Known Activations