© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13369
    Prev
    Next
    INDEX
    Explanations

    concepts related to vision, leadership, and future planning

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

    "vision" or related words

    np_acts-logits-general · gemini-2.0-flash

    future visions and plans

    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
     umgekehrt
    -0.35
    argmax
    -0.35
    matitis
    -0.35
    timewa
    -0.34
     bienes
    -0.33
     démocr
    -0.33
     fidèles
    -0.33
     habituellement
    -0.33
    argmin
    -0.33
    onucleotide
    -0.32
    POSITIVE LOGITS
     vision
    1.04
     visions
    0.94
     dreams
    0.92
     plans
    0.91
     envision
    0.91
     ambitions
    0.89
     visionary
    0.88
    Plans
    0.85
    dreams
    0.83
     envisioned
    0.83
    Activations Density 0.403%

    No Known Activations