© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-GEMMASCOPE-RES-16K
    11. 13728
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal charges and sentencing durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.54
     sede
    -0.49
     cobre
    -0.47
     Trock
    -0.46
    蒜
    -0.44
     Spielen
    -0.44
    отно
    -0.43
    uage
    -0.43
     bandera
    -0.42
    orgs
    -0.42
    POSITIVE LOGITS
     prison
    1.48
     jail
    1.40
     imprisonment
    1.35
    Prison
    1.26
     incarceration
    1.25
     Prison
    1.24
     PRISON
    1.19
    prison
    1.15
     imprisoned
    1.14
     incarcerated
    1.10
    Activations Density 0.314%

    No Known Activations