© 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. 11-GEMMASCOPE-RES-16K
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional relationships or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    horst
    -0.63
    راز
    -0.54
    zani
    -0.53
    werf
    -0.53
     weg
    -0.51
    brochen
    -0.50
    nativeElement
    -0.48
    zeta
    -0.48
    สือ
    -0.47
    ضايا
    -0.47
    POSITIVE LOGITS
     depending
    1.05
    depending
    1.01
    Depending
    0.97
     Depending
    0.95
     whether
    0.86
    según
    0.85
     afhankelijk
    0.83
     dipende
    0.83
     حسب
    0.83
     depender
    0.81
    Activations Density 0.220%

    No Known Activations