© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7571
    Prev
    Next
    INDEX
    Explanations

    content creators and their activities related to producing original media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppendLine
    -0.37
    SQLiteDatabase
    -0.36
     gynhyrchwyd
    -0.34
    Reprints
    -0.34
    endregion
    -0.33
     sätta
    -0.33
     sorri
    -0.32
    SRAM
    -0.31
     http
    -0.31
    http
    -0.31
    POSITIVE LOGITS
     influencer
    1.45
     YouTuber
    1.43
     influencers
    1.41
     TikTok
    1.40
     youtuber
    1.35
     YouTube
    1.28
     Influencer
    1.23
     vlog
    1.23
     tiktok
    1.21
     Tiktok
    1.21
    Activations Density 0.198%

    No Known Activations