© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9436
    Prev
    Next
    INDEX
    Explanations

    specific visual attributes of objects, particularly colors and shapes

    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
    oredCriteria
    -0.75
    principalTable
    -0.73
    sizeCache
    -0.70
    fjspx
    -0.59
    InsertCommand
    -0.58
    IUrlHelper
    -0.57
    agré
    -0.55
    RepeatedField
    -0.54
    NameInMap
    -0.53
    TintMode
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    +#+
    0.64
    __((
    0.59
    佑
    0.50
     topped
    0.49
    reactstrap
    0.48
     Tapatalk
    0.47
    __":
    0.47
    幢
    0.47
    anything
    0.46
    Activations Density 0.670%

    No Known Activations