© 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. 4-GEMMASCOPE-RES-16K
    6. 10581
    Prev
    Next
    INDEX
    Explanations

    structural elements of code or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.69
    tvguidetime
    -0.61
    ISupport
    -0.60
    :][
    -0.59
    Datuak
    -0.58
    ">//
    -0.57
    GraphicsUnit
    -0.57
    сылкі
    -0.56
    WillAppear
    -0.55
     createSprite
    -0.54
    POSITIVE LOGITS
     picioare
    0.47
     umane
    0.47
    ebabkan
    0.45
    asının
    0.45
    例文帳に追加
    0.45
    anical
    0.45
    ligente
    0.45
    пі
    0.44
    viève
    0.43
    พร
    0.43
    Activations Density 0.260%

    No Known Activations