© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    HTML header tags

    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
    Personensuche
    -0.74
    PerformLayout
    -0.73
    出版年
    -0.73
    SBATCH
    -0.72
    DebuggerStep
    -0.71
    spesies
    -0.68
    mability
    -0.67
     LIM
    -0.67
    entee
    -0.65
     Reverso
    -0.64
    POSITIVE LOGITS
    <h2>
    0.64
     clés
    0.56
    pulumi
    0.50
     chiave
    0.47
     kasarigan
    0.47
     viewDidLoad
    0.45
     autrement
    0.42
     concorso
    0.42
     particuliers
    0.42
     gammel
    0.42
    Activations Density 0.368%

    No Known Activations