© 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. 17-GEMMASCOPE-RES-16K
    6. 13737
    Prev
    Next
    INDEX
    Explanations

    locations and spatial descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.73
    GUILayout
    -0.56
    pery
    -0.55
     atmosfer
    -0.54
    brigens
    -0.54
    IUrlHelper
    -0.54
    NOPQRST
    -0.54
    κτηρισ
    -0.53
    WAUKEE
    -0.53
    SEGUIR
    -0.52
    POSITIVE LOGITS
     where
    0.72
    elemField
    0.66
     Ecu
    0.63
    where
    0.55
    تقاوى
    0.53
     donde
    0.52
     Himo
    0.52
    TagMode
    0.52
    neath
    0.51
     acostumb
    0.51
    Activations Density 0.256%

    No Known Activations