© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 114787
    Prev
    Next
    INDEX
    Explanations

    key features and characteristics that define concepts or phenomena, particularly in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Administrativna
    -0.73
    ſſung
    -0.71
    iſche
    -0.69
     deſſen
    -0.68
     protoimpl
    -0.68
     Dieſe
    -0.68
    <unused51>
    -0.67
    ſicht
    -0.67
    <unused8>
    -0.66
    <unused14>
    -0.66
    POSITIVE LOGITS
     here
    0.35
     throughout
    0.35
     Bestandteil
    0.35
     for
    0.33
     of
    0.33
    aarrggbb
    0.32
    attraction
    0.32
     atra
    0.31
     when
    0.30
     available
    0.30
    Activations Density 0.057%

    No Known Activations