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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 141
    Prev
    Next
    INDEX
    Explanations

    concepts related to consciousness and awareness in cognitive processes

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

    after "conscious" or related terms

    np_acts-logits-general · gemini-2.0-flash

    conscious awareness and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •harmless_evil_confidant_18

    No Comments

    Negative Logits
     cháy
    -0.56
    enig
    -0.54
    Jeografia
    -0.52
     équ
    -0.51
    dragen
    -0.51
     istitu
    -0.50
    EventQueue
    -0.49
     Mak
    -0.49
     rispet
    -0.48
     disediakan
    -0.48
    POSITIVE LOGITS
     conscious
    1.44
     consciously
    1.41
    conscious
    1.20
     Conscious
    1.18
     consciousness
    1.16
     subconscious
    1.14
    Conscious
    1.14
     consci
    1.05
     unconscious
    1.05
    consciousness
    1.03
    Activations Density 0.295%

    No Known Activations