© 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. 12587
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss financial implications and personal responsibility

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

    Followed by "many", "whether", "who", "those", or "half"

    np_acts-logits-general · gemini-2.0-flash

    many

    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
    Autoritní
    -0.57
     kasarigan
    -0.56
     EconPapers
    -0.48
    oa̍t
    -0.47
    RTLR
    -0.46
    exitRule
    -0.42
    ButtonModule
    -0.41
    senz
    -0.41
    ernalia
    -0.41
     Wicidata
    -0.40
    POSITIVE LOGITS
     many
    2.36
     some
    2.09
     algunos
    1.92
     многих
    1.90
    many
    1.89
     многие
    1.89
     некоторые
    1.87
     некоторых
    1.84
     muchos
    1.83
     niektórych
    1.81
    Activations Density 2.297%

    No Known Activations