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. 24-GEMMASCOPE-RES-16K
    6. 13932
    Prev
    Next
    INDEX
    Explanations

    statements related to spiritual beliefs and divine authority

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

    Quotes followed by a verb of believing/hearing

    np_acts-logits-general · gemini-2.0-flash

    introductory quoted speech

    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
    djangoproject
    -0.66
    sidemargin
    -0.55
     referenties
    -0.51
    IContainer
    -0.50
    Abit
    -0.49
    messageInfo
    -0.49
    fiq
    -0.48
    olis
    -0.48
    olm
    -0.48
    ;"></
    -0.47
    POSITIVE LOGITS
     Therefore
    0.67
     Thou
    0.64
     Behold
    0.63
     FetchType
    0.62
     behold
    0.60
    Therefore
    0.60
     Oh
    0.60
     Truly
    0.60
     Let
    0.59
     verily
    0.58
    Activations Density 0.090%

    No Known Activations