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. 1-GEMMASCOPE-RES-16K
    6. 14984
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intent, specifically the word "to."

    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
    makeConstraints
    -0.69
    Vidite
    -0.65
     surla
    -0.65
    CGRectMake
    -0.62
     Misalnya
    -0.62
    Види
    -0.61
    InlineData
    -0.61
    ïa
    -0.61
    extAlignment
    -0.60
    ')['
    -0.58
    POSITIVE LOGITS
     to
    0.81
     να
    0.78
    ที่จะ
    0.78
     To
    0.73
    To
    0.72
     skall
    0.70
     să
    0.66
     TO
    0.66
     чтобы
    0.65
    จะ
    0.65
    Activations Density 1.137%

    No Known Activations