© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 3443
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rare" along with its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odeon
    -0.72
    readlines
    -0.65
     Bender
    -0.65
    intellij
    -0.63
    mbros
    -0.63
    cdk
    -0.61
    iços
    -0.56
     Milit
    -0.55
    Abitanti
    -0.54
    getComponent
    -0.53
    POSITIVE LOGITS
     rare
    1.95
     Rare
    1.81
    Rare
    1.69
     rarity
    1.66
     rarer
    1.65
    rare
    1.64
     RARE
    1.57
     rares
    1.51
     rarest
    1.42
     rara
    1.39
    Activations Density 0.112%

    No Known Activations