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. 23-GEMMASCOPE-RES-16K
    6. 6218
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts, especially those related to holiness and the divine

    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
    AccessorTable
    -1.16
     EconPapers
    -1.08
     صوتيه
    -1.06
    httphttps
    -0.91
    ViewFeatures
    -0.91
    InSection
    -0.90
    setopt
    -0.86
     الحره
    -0.86
     CreateTagHelper
    -0.83
    RectangleBorder
    -0.82
    POSITIVE LOGITS
    oke
    0.70
     Spirit
    0.69
     Ghost
    0.66
    Spirit
    0.62
     grail
    0.62
     spirit
    0.58
     Land
    0.58
    Ghost
    0.58
    scriptcase
    0.56
     Trinity
    0.56
    Activations Density 0.143%

    No Known Activations