© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15753
    Prev
    Next
    INDEX
    Explanations

    information about personal development and self-improvement

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

    Following "our" or related to spirituality

    np_acts-logits-general · gemini-2.0-flash

    sacred Ganja plant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     microfilm
    -0.64
    öhnt
    -0.63
     riuscito
    -0.59
    存于互联网档案馆
    -0.59
     maxn
    -0.58
     aggressiveness
    -0.58
    StateList
    -0.56
    Schemes
    -0.56
     rivales
    -0.55
    Eksterne
    -0.55
    POSITIVE LOGITS
     honoring
    0.74
     energetically
    0.74
     sacred
    0.74
     nourishing
    0.71
     intuitively
    0.69
     deepening
    0.68
     Sacred
    0.68
     healing
    0.67
     deepen
    0.67
    Sacred
    0.67
    Activations Density 0.464%

    No Known Activations