© 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. 30-GEMMASCOPE-RES-16K
    11. 10705
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings, particularly concerning sentence and parole issues

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

    preceding "of" or possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usarlo
    -0.46
    ListItemIcon
    -0.43
     oneself
    -0.39
    因为它
    -0.38
     AssemblyCompany
    -0.38
    ngdoc
    -0.37
    itself
    -0.35
    myself
    -0.35
    XmlAccessType
    -0.34
     themselves
    -0.33
    POSITIVE LOGITS
     peoples
    0.96
    别人的
    0.89
    对方的
    0.86
     his
    0.84
    大家的
    0.79
     deren
    0.79
     childrens
    0.77
     hänen
    0.77
    学生的
    0.76
    用户的
    0.76
    Activations Density 1.387%

    No Known Activations