© 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. 769
    Prev
    Next
    INDEX
    Explanations

    thoughts and reflections on personal experiences and considerations

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

    "Think" or "consider" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    thinking about something specific

    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
     gai
    -0.41
     VIDEOTAPE
    -0.41
    のです
    -0.35
    のですか
    -0.34
    enable
    -0.33
    んでしょう
    -0.31
     finally
    -0.31
    enschaften
    -0.31
    のでしょう
    -0.31
     hopefully
    -0.30
    POSITIVE LOGITS
     thinking
    0.92
     thoughts
    0.92
    Think
    0.91
    Thinking
    0.91
     THINK
    0.90
     considerations
    0.90
     Think
    0.89
     생각
    0.89
    THINK
    0.88
     consideration
    0.88
    Activations Density 0.196%

    No Known Activations