© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    call-to-action phrases related to trying or testing things

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

    tests or trials

    np_acts-logits-general · gemini-2.0-flash

    free trial, testing, test

    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
    stdc
    -0.59
    OCCURRED
    -0.56
     DialogInterface
    -0.52
    ResumeLayout
    -0.51
    PerformLayout
    -0.48
     kaynağından
    -0.48
    nloa
    -0.47
    ardige
    -0.46
    iaceae
    -0.46
     onPage
    -0.45
    POSITIVE LOGITS
     testing
    2.26
     test
    2.24
     trial
    2.08
     tests
    1.98
     Testing
    1.97
     tested
    1.95
     trials
    1.87
    Testing
    1.86
     Test
    1.84
     tester
    1.80
    Activations Density 0.496%

    No Known Activations