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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5306
    Prev
    Next
    INDEX
    Explanations

    concepts related to religious beliefs and values

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

    "creation" and "created"

    np_acts-logits-general · gemini-2.0-flash

    creation and origins of the universe

    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
    tagHelperRunner
    -0.90
    rungsseite
    -0.84
    oa̍t
    -0.78
    ValueStyle
    -0.77
    DoubleQuotes
    -0.76
     onOptions
    -0.63
    UnusedPrivate
    -0.63
    "])
    -0.62
     betweenstory
    -0.62
    UnsafeEnabled
    -0.60
    POSITIVE LOGITS
     creation
    1.28
     Creation
    1.22
    creation
    1.13
    Creation
    1.13
     created
    1.07
     Created
    0.99
     création
    0.97
     Création
    0.93
    created
    0.91
     خل
    0.90
    Activations Density 0.223%

    No Known Activations