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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 834
    Prev
    Next
    INDEX
    Explanations

    concepts of truth and authenticity

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

    truth, genuineness, and reality

    np_acts-logits-general · gemini-2.0-flash

    genuine or real quality

    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
    vode
    -0.41
    past
    -0.36
    otherwise
    -0.34
     previously
    -0.33
     Otherwise
    -0.32
    related
    -0.32
     fjor
    -0.32
     mort
    -0.32
     denk
    -0.32
     otherwise
    -0.31
    POSITIVE LOGITS
     true
    0.88
     prawdzi
    0.80
     real
    0.77
     TRUE
    0.76
     genuine
    0.75
     truly
    0.72
    enuine
    0.72
    真正的
    0.71
     verdadeira
    0.71
     REAL
    0.70
    Activations Density 0.245%

    No Known Activations