© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7005
    Prev
    Next
    INDEX
    Explanations

    statistical references to trends or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.69
     CreateTagHelper
    -0.60
    endphp
    -0.45
    rdquo
    -0.45
     interesar
    -0.45
    sac
    -0.42
     thẳng
    -0.42
    feinander
    -0.42
    oches
    -0.41
    soe
    -0.41
    POSITIVE LOGITS
     just
    1.74
    just
    1.54
    Just
    1.33
     Just
    1.30
     JUST
    1.21
    JUST
    1.17
     merely
    1.13
    只是
    1.10
     juſt
    1.04
     лишь
    1.02
    Activations Density 0.153%

    No Known Activations