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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1378
    Prev
    Next
    INDEX
    Explanations

    expressions of thought, belief, or opinion

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

    followed by "think" or "thought"

    np_acts-logits-general · gemini-2.0-flash

    thoughts and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Byers
    -0.39
     mukana
    -0.37
     bedrijfs
    -0.36
     Rojas
    -0.35
     •
    -0.35
     Farrell
    -0.35
     for
    -0.35
    />";
    -0.35
     Salas
    -0.35
     SEC
    -0.34
    POSITIVE LOGITS
    RectangleBorder
    0.77
    Personendaten
    0.68
     think
    0.68
    Think
    0.66
     Think
    0.66
    think
    0.64
     thinks
    0.63
     THINK
    0.61
     propOrder
    0.57
    THINK
    0.56
    Activations Density 0.173%

    No Known Activations