© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4258
    Prev
    Next
    INDEX
    Explanations

    certain introductory phrases or markers indicating the beginning of a discussion or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XMLSchema
    -0.69
     виправивши
    -0.57
    RUnlock
    -0.56
    PreferredItem
    -0.55
    帖最后由
    -0.55
    riwal
    -0.53
     Factbook
    -0.52
    المشاركات
    -0.52
    AndEndTag
    -0.51
     curé
    -0.51
    POSITIVE LOGITS
    Kjelder
    0.61
     незавершена
    0.60
    uldig
    0.58
     ⁠
    0.55
     swears
    0.54
    layed
    0.53
     enggak
    0.52
     nggak
    0.51
    €”
    0.51
     lesquels
    0.51
    Activations Density 0.183%

    No Known Activations