© 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. 12-GEMMASCOPE-RES-16K
    6. 14130
    Prev
    Next
    INDEX
    Explanations

    references to advanced or cutting-edge concepts and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesia
    -0.82
    lück
    -0.71
     KPMG
    -0.71
    roffene
    -0.71
    ooplankton
    -0.70
    ibrill
    -0.69
    rillation
    -0.69
    wußt
    -0.66
    Krak
    -0.66
    SqlClient
    -0.65
    POSITIVE LOGITS
     Advance
    1.48
     ADVANCE
    1.46
     advance
    1.45
    Advance
    1.40
     advances
    1.39
     advanced
    1.30
     Advances
    1.30
     ADVANCED
    1.26
    advanced
    1.26
     Advanced
    1.25
    Activations Density 0.087%

    No Known Activations