© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    dialogues and interactions involving characters and emotional responses

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    later, afterwards, lesson

    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
     progressively
    -0.50
     IBOutlet
    -0.46
     continually
    -0.44
    MessageOf
    -0.44
    我先
    -0.44
     continuously
    -0.44
    цездатний
    -0.43
    まず
    -0.43
     vượt
    -0.42
     pasada
    -0.42
    POSITIVE LOGITS
     lesson
    0.84
     Lesson
    0.80
    Later
    0.79
    Lesson
    0.79
     afterwards
    0.77
     Later
    0.77
    Moral
    0.75
    later
    0.75
     later
    0.75
    Afterwards
    0.73
    Activations Density 0.445%

    No Known Activations