© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 336
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their treatment

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

    Preceding "once," "as," or "if"

    np_acts-logits-general · gemini-2.0-flash

    at least once

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.57
     متعلقه
    -0.53
     jsPsych
    -0.47
     preceding
    -0.47
    aspectj
    -0.47
    ってきました
    -0.45
    Allora
    -0.43
    sider
    -0.42
    angos
    -0.41
     تعدى
    -0.41
    POSITIVE LOGITS
     once
    3.99
    once
    3.52
    Once
    3.50
     Once
    3.50
     ONCE
    2.96
    ONCE
    2.88
    一旦
    2.09
     einmal
    1.95
     Sobald
    1.81
     sekali
    1.59
    Activations Density 0.338%

    No Known Activations