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. 8-GEMMASCOPE-RES-16K
    6. 9131
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality and relativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.88
     pData
    -0.72
    rąg
    -0.72
    例句
    -0.72
     Ponta
    -0.72
     Oyo
    -0.71
     XLV
    -0.71
     JSTOR
    -0.70
     tucson
    -0.70
     Pala
    -0.70
    POSITIVE LOGITS
     least
    1.34
    jmniej
    1.09
     atleast
    1.02
    least
    1.00
    Least
    1.00
     almeno
    1.00
     LEAST
    0.95
     Least
    0.92
     setidaknya
    0.91
    至少
    0.91
    Activations Density 0.083%

    No Known Activations