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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3948
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.76
    "><?
    -0.75
     themſelves
    -0.74
     principes
    -0.72
     Schweitzer
    -0.71
     Efq
    -0.70
     purpoſe
    -0.70
     ſmall
    -0.69
     exceso
    -0.69
    ?></
    -0.69
    POSITIVE LOGITS
     b
    1.94
    b
    1.80
    ｂ
    1.04
     bVar
    0.91
     ب
    0.87
    Xb
    0.82
    bIs
    0.82
    𝐛
    0.81
    bA
    0.80
     c
    0.80
    Activations Density 0.158%

    No Known Activations