Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6115
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISPR
    -0.63
     démocr
    -0.60
    envolvimento
    -0.57
     miniatura
    -0.55
    Sega
    -0.55
    lső
    -0.55
    IBOutlet
    -0.52
     recommandons
    -0.51
    ;->
    -0.51
     türlü
    -0.51
    POSITIVE LOGITS
     hay
    2.73
     Hay
    2.63
    Hay
    2.42
     HAY
    2.34
    HAY
    2.08
    hay
    1.95
     haystack
    1.29
     Haynes
    0.94
     haya
    0.94
     Hayat
    0.93
    Activations Density 0.032%

    No Known Activations