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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2096
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Not only" phrases

    np_acts-logits-general · gemini-2.0-flash

    not only... but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     InputDecoration
    -0.48
     BaseActivity
    -0.42
    CHOICES
    -0.40
     LoginForm
    -0.40
    hrs
    -0.40
     vêtement
    -0.38
     código
    -0.38
     maf
    -0.37
     Kenn
    -0.37
     kenn
    -0.37
    POSITIVE LOGITS
    owohl
    0.69
    VersionUID
    0.62
     nejen
    0.57
    تقاوى
    0.56
    wnież
    0.54
    それだけ
    0.52
    不仅仅
    0.51
    NotEmpty
    0.51
     بلکه
    0.50
    Neben
    0.49
    Activations Density 0.070%

    No Known Activations