© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 16041
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strong" related to various contexts or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.73
    GetMapping
    -0.68
    XmlAccessorType
    -0.65
     interchangeably
    -0.64
     Tutu
    -0.64
    verifyException
    -0.63
     mayhem
    -0.63
    눠
    -0.62
    റ
    -0.61
     Bliss
    -0.61
    POSITIVE LOGITS
     strong
    3.26
     Strong
    3.06
    strong
    3.05
    Strong
    3.00
     STRONG
    2.85
    STRONG
    2.67
     stronger
    2.25
     strongest
    2.15
     sterke
    2.10
     Stronger
    1.95
    Activations Density 0.075%

    No Known Activations