© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13869
    Prev
    Next
    INDEX
    Explanations

    terms related to opportunities and potential for growth or expansion

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

    new potential or opportunities

    np_acts-logits-general · gemini-2.0-flash

    opening new possibilities

    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
    ThroughAttribute
    -0.45
     Abstand
    -0.40
    Наводи
    -0.40
    loroethane
    -0.40
    ismet
    -0.39
    Watched
    -0.39
     Zink
    -0.38
    Попис
    -0.38
    jercicio
    -0.38
    lastTime
    -0.38
    POSITIVE LOGITS
     possibilities
    0.82
     horizons
    0.72
     mogelijkheden
    0.66
     opportunities
    0.65
     Possibilities
    0.65
     możliwości
    0.64
     possibilidades
    0.63
     expand
    0.60
     expanding
    0.60
     expansion
    0.59
    Activations Density 0.249%

    No Known Activations