© 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. 0-GEMMASCOPE-RES-16K
    6. 8679
    Prev
    Next
    INDEX
    Explanations

    technical and legal terminology related to programming and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.63
     verksamhet
    -0.62
     typelib
    -0.58
    TemporalType
    -0.57
    quelize
    -0.57
     ligiloj
    -0.54
    delwed
    -0.53
     MonoBehaviour
    -0.52
     فريبيس
    -0.52
    DotNetBar
    -0.52
    POSITIVE LOGITS
    seal
    0.67
     migrant
    0.65
     border
    0.63
     BORDER
    0.60
     Sealing
    0.59
     Border
    0.58
    bod
    0.58
    Border
    0.58
     seal
    0.58
    thalt
    0.57
    Activations Density 2.310%

    No Known Activations