Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6394
    Prev
    Next
    INDEX
    Explanations

    expressions of thought or contemplation

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

    "think" or "thinking"

    np_acts-logits-general · gemini-2.0-flash

    thinking about or asking about

    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
     Guill
    -0.47
     »
    -0.46
     Kob
    -0.44
     «
    -0.44
    <eos>
    -0.42
    я
    -0.41
    »
    -0.41
    «
    -0.40
     Jacobsen
    -0.40
     Quig
    -0.40
    POSITIVE LOGITS
     THINK
    1.74
     think
    1.74
    Think
    1.73
     Think
    1.72
    think
    1.68
    THINK
    1.59
     thinks
    1.54
     thinking
    1.41
     Thinking
    1.36
    thinking
    1.34
    Activations Density 0.179%

    No Known Activations