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. 21-GEMMASCOPE-RES-16K
    6. 15135
    Prev
    Next
    INDEX
    Explanations

    phrases that express relations of necessity or obligation

    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
    PositiveButton
    -0.56
     ***!
    -0.56
     resourceCulture
    -0.55
     soort
    -0.55
     Commencez
    -0.54
    fromnode
    -0.53
     Diſ
    -0.52
    kmäler
    -0.52
    idians
    -0.52
    جوايز
    -0.51
    POSITIVE LOGITS
     do
    2.06
    do
    1.70
     Do
    1.48
    Do
    1.47
     DO
    1.37
    DO
    1.15
     does
    1.10
     propOrder
    0.91
     doe
    0.88
     до
    0.84
    Activations Density 0.096%

    No Known Activations