© 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. 21-GEMMASCOPE-RES-16K
    6. 2600
    Prev
    Next
    INDEX
    Explanations

    concepts related to knowledge and its pursuit in a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.94
    RenderAtEndOf
    -0.89
     مرئيه
    -0.75
    aarrggbb
    -0.75
     متعلقه
    -0.73
    Autoritní
    -0.72
    Personensuche
    -0.71
     дописавши
    -0.70
    setVerticalGroup
    -0.67
     تانيه
    -0.66
    POSITIVE LOGITS
     peace
    0.62
    picasso
    0.46
     PEACE
    0.45
     Peace
    0.44
    Peace
    0.44
    peace
    0.44
    SAW
    0.43
     ver
    0.43
     SAW
    0.42
    tvguidetime
    0.41
    Activations Density 0.097%

    No Known Activations