© 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. 0-GEMMASCOPE-RES-16K
    11. 11466
    Prev
    Next
    INDEX
    Explanations

    titles or phrases indicating actions, particularly related to discovery or reporting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.16
     in
    -1.10
     (
    -1.02
    ,
    -1.01
     for
    -0.96
     and
    -0.96
     de
    -0.94
     is
    -0.94
     a
    -0.93
    <eos>
    -0.93
    POSITIVE LOGITS
     myſelf
    2.41
     Theſe
    2.36
     Monfieur
    2.34
     itſelf
    2.25
     Efq
    2.21
     Jefus
    2.20
     ſeveral
    2.17
     faſt
    2.13
     ſever
    2.11
     Reſ
    2.11
    Activations Density 0.222%

    No Known Activations