© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14766
    Prev
    Next
    INDEX
    Explanations

    criteria and requirements for student promotion in educational contexts

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

    "credit", "credits", or "CFR"

    np_acts-logits-general · gemini-2.0-flash

    credit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.60
    uteurs
    -0.59
    Disliked
    -0.56
    isand
    -0.53
    فاق
    -0.52
    HandleFunc
    -0.52
    favourite
    -0.51
     anat
    -0.51
    ┛
    -0.50
     robusta
    -0.50
    POSITIVE LOGITS
     credits
    1.09
     credit
    1.08
     Credits
    0.92
     Credit
    0.91
    credit
    0.84
    credits
    0.83
     CREDIT
    0.82
    Credit
    0.78
     CREDITS
    0.77
     créditos
    0.75
    Activations Density 0.125%

    No Known Activations