© 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. 23-GEMMASCOPE-RES-16K
    11. 15257
    Prev
    Next
    INDEX
    Explanations

    actions, particularly those involving giving or transferring responsibility or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    they
    -0.74
     AssemblyCulture
    -0.66
     cuando
    -0.62
    when
    -0.62
     porque
    -0.61
     они
    -0.60
     anún
    -0.60
     вони
    -0.59
     dégâts
    -0.58
    cuando
    -0.57
    POSITIVE LOGITS
     aside
    1.04
     down
    0.83
     off
    0.83
     us
    0.82
     up
    0.77
     them
    0.76
     forth
    0.75
     out
    0.75
     apart
    0.73
     the
    0.72
    Activations Density 0.481%

    No Known Activations