© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9033
    Prev
    Next
    INDEX
    Explanations

    actions and choices related to decision-making and transition

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

    implying alternatives or different options

    np_acts-logits-general · gemini-2.0-flash

    alternative or elsewhere

    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
     tutti
    -0.32
     tous
    -0.31
    aksikan
    -0.30
    要知道
    -0.29
     suivi
    -0.29
    #!/
    -0.29
     dabei
    -0.29
    发生的
    -0.28
     nä
    -0.28
    engaruhi
    -0.28
    POSITIVE LOGITS
     elsewhere
    1.91
     Elsewhere
    1.48
     ailleurs
    1.38
    Elsewhere
    1.32
     alternatives
    1.14
     altro
    1.12
    別の
    1.12
     alternative
    1.11
     another
    1.11
     başka
    1.09
    Activations Density 0.537%

    No Known Activations