© 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. 10-GEMMASCOPE-RES-16K
    11. 10214
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strong" and its variations, indicating a focus on strength or robustness 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 @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upaten
    -0.70
    Datuak
    -0.69
     Maus
    -0.68
    Loot
    -0.67
    kaido
    -0.66
     oblivion
    -0.65
    Joc
    -0.64
    enumi
    -0.64
    goTo
    -0.63
     Miyazaki
    -0.63
    POSITIVE LOGITS
    strong
    1.60
    STRONG
    1.58
     Strong
    1.58
    Strong
    1.54
     STRONG
    1.50
     strong
    1.45
    strength
    1.45
     strength
    1.33
    ngths
    1.32
     Strength
    1.31
    Activations Density 0.084%

    No Known Activations