© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11233
    Prev
    Next
    INDEX
    Explanations

    details related to structured training and educational methods in clinical settings

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

    Hands-on, interactive, or practical training/experience

    np_acts-logits-general · gemini-2.0-flash

    practical training and workshops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ulang
    -0.53
    ngOnInit
    -0.51
     Entfer
    -0.50
     EconPapers
    -0.48
    ])));
    -0.48
     vuo
    -0.47
    億
    -0.46
     bilhões
    -0.46
     spite
    -0.45
    tomatik
    -0.45
    POSITIVE LOGITS
     practical
    0.97
     experiential
    0.92
    practical
    0.91
     interactive
    0.90
     hands
    0.89
     exercises
    0.87
    hands
    0.87
     practi
    0.86
     practice
    0.83
     immersion
    0.83
    Activations Density 0.260%

    No Known Activations