© 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. 25-GEMMASCOPE-RES-16K
    11. 15146
    Prev
    Next
    INDEX
    Explanations

    elements related to legal terminology and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ADVISORY
    -0.67
     دیکھیے
    -0.66
     Advisory
    -0.64
     surveys
    -0.62
     advisory
    -0.60
     Cluster
    -0.60
     survey
    -0.60
     indag
    -0.60
     Clusters
    -0.60
     Survey
    -0.59
    POSITIVE LOGITS
     female
    0.53
     pronunciation
    0.51
    female
    0.48
     handwriting
    0.47
     visual
    0.47
     visually
    0.45
    frauen
    0.45
    bcryptjs
    0.44
     pronouns
    0.44
     Visual
    0.44
    Activations Density 2.420%

    No Known Activations