© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29465
    Prev
    Next
    INDEX
    Explanations

    phrases indicating findings or results in a scholarly context

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

    already

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.52
    DotNetBar
    -0.50
     unique
    -0.48
    putInt
    -0.44
    นวน
    -0.43
    ונה
    -0.43
    SharedDtor
    -0.42
    unique
    -0.42
    ungere
    -0.42
    ıdır
    -0.41
    POSITIVE LOGITS
     already
    1.42
    already
    1.30
     Already
    1.19
    Already
    1.16
     déjà
    1.10
     ALREADY
    1.10
     allerede
    1.03
     redan
    1.00
     이미
    0.96
    ALREADY
    0.96
    Activations Density 0.633%

    No Known Activations