© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56954
    Prev
    Next
    INDEX
    Explanations

    phrases related to scenic views and landscapes

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

    views particularly

    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-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
     ProtoMessage
    -0.71
     informée
    -0.64
     autorytatywna
    -0.63
     ब्रेकडाउन
    -0.58
    Izvori
    -0.58
    majánló
    -0.57
     myſelf
    -0.55
     pinulongan
    -0.54
    цездатний
    -0.53
    expandindo
    -0.52
    POSITIVE LOGITS
     beautiful
    0.49
     view
    0.45
     panor
    0.42
    beautiful
    0.42
     panoramic
    0.41
     BoxFit
    0.41
    🌅
    0.40
    IntoConstraints
    0.40
     sunsets
    0.40
     sunset
    0.40
    Activations Density 0.131%

    No Known Activations