© 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. 23-GEMMASCOPE-RES-16K
    6. 8611
    Prev
    Next
    INDEX
    Explanations

    religious concepts and terms related to salvation and faith

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    κτηρισ
    -0.63
    ècie
    -0.57
     nightmare
    -0.56
    Mucha
    -0.54
    nightmare
    -0.52
     curious
    -0.51
     Mucha
    -0.51
     hectic
    -0.50
     Curious
    -0.50
     مشين
    -0.50
    POSITIVE LOGITS
    basicConfig
    0.70
     unto
    0.66
    CodeAttribute
    0.60
     forever
    0.60
     eternally
    0.54
     maternelle
    0.54
    ruptedException
    0.53
     estaremos
    0.52
    iastes
    0.51
     affinch
    0.51
    Activations Density 0.225%

    No Known Activations