© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1505
    Prev
    Next
    INDEX
    Explanations

    terms related to hobbies and amateur activities

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

    "Hobby" and "enthusiast" contexts

    np_acts-logits-general · gemini-2.0-flash

    amateur hobby enthusiasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.61
     noDo
    -0.59
     يتيمه
    -0.58
    WebElementEntity
    -0.58
    AccessorTable
    -0.56
    RegressionTest
    -0.54
    enterOuterAlt
    -0.54
    exitRule
    -0.52
    ništvo
    -0.51
     الحره
    -0.49
    POSITIVE LOGITS
     hobby
    1.16
    hobby
    0.89
     Hobby
    0.85
    Hobby
    0.84
     amateur
    0.83
    Amateur
    0.81
     Amateur
    0.80
     hobbies
    0.80
     amateurs
    0.78
     enthusiast
    0.78
    Activations Density 0.231%

    No Known Activations