© 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. 17-GEMMASCOPE-RES-16K
    11. 9567
    Prev
    Next
    INDEX
    Explanations

    code structures and definitions related to data types and memory allocation

    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
    rillos
    -0.54
    Iné
    -0.48
    keen
    -0.48
    تقاوى
    -0.47
    phens
    -0.47
    Spoljašnje
    -0.47
    vorm
    -0.46
     insuffisamment
    -0.46
     ado
    -0.45
    حياتها
    -0.45
    POSITIVE LOGITS
     *
    1.58
    *
    1.51
    (*
    1.35
     (*
    1.18
    =*
    1.18
    ,*
    1.14
     $*$
    1.03
    .*
    1.02
    *,
    1.01
    :*
    0.99
    Activations Density 0.401%

    No Known Activations