© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10212
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rights and due process in court proceedings

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

    legal "trial" contexts

    np_acts-logits-general · gemini-2.0-flash

    rights to a fair trial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Astrid
    -0.49
     Nid
    -0.46
    sonaro
    -0.46
    glises
    -0.45
    UrlResolution
    -0.44
    Rüyada
    -0.44
     Numerade
    -0.44
    Astrid
    -0.43
    :+:
    -0.43
     Infórmanos
    -0.43
    POSITIVE LOGITS
     trial
    0.68
    trial
    0.60
     TRIAL
    0.56
     Trial
    0.56
    Trial
    0.49
     trials
    0.45
    trials
    0.42
    Processo
    0.42
    zeß
    0.40
     MainAxisSize
    0.40
    Activations Density 1.879%

    No Known Activations