© 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. 5255
    Prev
    Next
    INDEX
    Explanations

    references to legal codes and sections in documents

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

    Restatement (Second) of Torts and similar citations

    np_acts-logits-general · gemini-2.0-flash

    section . c or . d

    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
    Vidite
    -0.69
     Roskov
    -0.60
     kaarangay
    -0.59
     <=",
    -0.56
    PMailer
    -0.55
    stateProvider
    -0.54
     Meksiku
    -0.54
    InitVars
    -0.53
    ोंने
    -0.51
    cuadro
    -0.50
    POSITIVE LOGITS
     d
    1.64
     b
    1.47
    d
    1.40
     c
    1.37
    b
    1.28
    c
    1.21
     g
    1.11
     f
    1.10
     h
    1.02
    g
    1.01
    Activations Density 1.425%

    No Known Activations