© 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. 12754
    Prev
    Next
    INDEX
    Explanations

    themes of connection and shared experiences in relationships

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

    Follows "are" or a form of "be."

    np_acts-logits-general · gemini-2.0-flash

    are not alone, qualified, welcome, right

    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
     proprement
    -0.46
     zijne
    -0.46
    clusal
    -0.44
     efectivo
    -0.44
     obé
    -0.44
     zelve
    -0.43
    aarrggbb
    -0.43
     Eſ
    -0.43
     cohé
    -0.43
     sfeer
    -0.42
    POSITIVE LOGITS
     worth
    0.77
     WORTH
    0.63
     valued
    0.62
     valuable
    0.62
    worth
    0.62
    WORTH
    0.57
    Worth
    0.56
     Würde
    0.56
     AssemblyCulture
    0.54
     worthy
    0.53
    Activations Density 0.246%

    No Known Activations