© 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. 9-GEMMASCOPE-RES-16K
    11. 1912
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate historical documentation or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    のこと
    -0.55
     way
    -0.53
    Véxase
    -0.49
    각주
    -0.49
    ніципа
    -0.48
    ASE
    -0.47
     kaynağından
    -0.46
     taba
    -0.46
     T
    -0.46
    aderas
    -0.45
    POSITIVE LOGITS
    +#+#
    0.75
    AsUp
    0.73
    THISDAY
    0.69
     Où
    0.68
    脚注の使い方
    0.68
    ніципалі
    0.67
     stället
    0.66
    ниципа
    0.66
    WriteTagHelper
    0.66
    cèse
    0.64
    Activations Density 0.354%

    No Known Activations