© 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. 24-GEMMASCOPE-RES-16K
    11. 5290
    Prev
    Next
    INDEX
    Explanations

    references to authors and citations within academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before names or identifiers with brackets

    np_acts-logits-general · gemini-2.0-flash

    names, and affiliations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -0.59
     Waray
    -0.51
    when
    -0.51
     terapé
    -0.49
     quando
    -0.49
     aktivitet
    -0.47
    cuando
    -0.47
    RenderAtEndOf
    -0.46
    quando
    -0.44
     "}
    -0.44
    POSITIVE LOGITS
    好在
    0.56
    thâu
    0.56
    hysema
    0.56
    SequentialGroup
    0.56
    DebuggerNonUser
    0.55
     ModelExpression
    0.54
    featureID
    0.53
    väg
    0.52
     MEA
    0.51
    anmoins
    0.51
    Activations Density 0.180%

    No Known Activations