© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8720
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings and courtroom decisions

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

    before "decision" or "decisions"

    np_acts-logits-general · gemini-2.0-flash

    reaching a decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageState
    -0.48
    +#+
    -0.46
    enderror
    -0.45
    AISSEE
    -0.45
    ModelAdmin
    -0.43
    UnusedPrivate
    -0.43
    #![
    -0.42
     papas
    -0.42
    ItemLayout
    -0.42
     disambiguazione
    -0.41
    POSITIVE LOGITS
     decision
    2.20
    decision
    1.84
     decisions
    1.82
     décision
    1.73
     Decision
    1.66
     decisión
    1.62
    Decision
    1.59
    decisions
    1.55
     Decisions
    1.55
     decisione
    1.52
    Activations Density 0.866%

    No Known Activations