© 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. 10911
    Prev
    Next
    INDEX
    Explanations

    summaries of research results and data characteristics

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

    Information presented in tables or figures

    np_acts-logits-general · gemini-2.0-flash

    is/are shown in tables

    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
    Viitteet
    -0.69
    createCanvas
    -0.66
    principalTable
    -0.66
    Decided
    -0.59
    ymce
    -0.52
    辞典
    -0.51
     Sequo
    -0.50
     eventdata
    -0.49
    Referring
    -0.48
    boru
    -0.47
    POSITIVE LOGITS
     given
    1.54
     presented
    1.29
     shown
    1.26
    given
    1.24
    presented
    1.03
     listed
    0.97
     depicted
    0.97
     provided
    0.96
     summarized
    0.93
     Given
    0.92
    Activations Density 0.723%

    No Known Activations