© 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 EvalsExportsAPI 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. 14178
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or issues related to bail and incarceration

    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
    cticut
    -0.53
    apimachinery
    -0.53
    ecma
    -0.49
    sedown
    -0.49
    DoubleQuotes
    -0.49
     Landwir
    -0.49
     getChild
    -0.48
     epi
    -0.48
    })));
    -0.47
    UrlResolution
    -0.47
    POSITIVE LOGITS
     bail
    1.42
     bond
    1.23
    Bail
    1.16
     Bail
    1.07
    bail
    1.05
     sureties
    0.98
    bond
    0.96
     bonds
    0.93
     Bond
    0.90
     surety
    0.89
    Activations Density 0.822%

    No Known Activations