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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14000
    Prev
    Next
    INDEX
    Explanations

    phrases indicating absence or lack of conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     normaux
    -0.49
     Händen
    -0.49
     démocr
    -0.48
     Decke
    -0.47
     Volkes
    -0.47
     marins
    -0.46
     acrylique
    -0.45
     énergétique
    -0.45
     dépos
    -0.44
     Hauteur
    -0.44
    POSITIVE LOGITS
     without
    1.28
    without
    1.28
    Without
    1.24
    WITHOUT
    1.23
     Without
    1.20
     WITHOUT
    1.17
    Ohne
    1.06
     Ohne
    0.96
     zonder
    0.96
     senza
    0.93
    Activations Density 0.071%

    No Known Activations