© 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. 22-GEMMASCOPE-RES-16K
    11. 8502
    Prev
    Next
    INDEX
    Explanations

    mentions of witnesses and their statements in legal contexts

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

    Testimony or witness accounts

    np_acts-logits-general · gemini-2.0-flash

    testimony and accusations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.62
     föres
    -0.53
    IntoConstraints
    -0.52
     ब्रेकडाउन
    -0.50
    Redirection
    -0.49
    chra
    -0.49
     femmin
    -0.49
     logits
    -0.49
     UNESCO
    -0.49
     scher
    -0.48
    POSITIVE LOGITS
     testimony
    1.20
     testified
    1.10
     testify
    1.09
     witness
    1.05
     testifying
    1.04
     testimonies
    1.01
    testi
    0.99
     testifies
    0.95
     testimonio
    0.94
    witness
    0.94
    Activations Density 0.905%

    No Known Activations