© 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 EvalsExportsAPI 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. 12062
    Prev
    Next
    INDEX
    Explanations

    instances of successful attempts or actions taken to achieve goals

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

    "managed to" or similar constructions

    np_acts-logits-general · gemini-2.0-flash

    managed to do something

    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
     future
    -0.33
     review
    -0.31
     teď
    -0.28
     revisión
    -0.28
     cuartos
    -0.27
     budú
    -0.27
     budou
    -0.27
     customers
    -0.27
     Öffentlichkeit
    -0.26
     présente
    -0.26
    POSITIVE LOGITS
     successfully
    1.00
    successfully
    0.99
     Successfully
    0.95
     riuscito
    0.94
    achieved
    0.91
     managed
    0.91
    Successfully
    0.90
     riusc
    0.88
    managed
    0.87
    IntoConstraints
    0.85
    Activations Density 0.258%

    No Known Activations