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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 195
    Prev
    Next
    INDEX
    Explanations

    references to proxy-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.54
     transfieras
    -0.51
    下载附件
    -0.51
    ficult
    -0.50
     wusste
    -0.49
     Alcal
    -0.49
    rha
    -0.49
    FieldBuilder
    -0.47
    žius
    -0.47
     Verhältnisse
    -0.47
    POSITIVE LOGITS
    Proxy
    0.80
     Proxy
    0.79
    proxy
    0.79
    OGND
    0.78
     proxy
    0.77
    expandindo
    0.75
     rowspan
    0.68
     mode
    0.67
     Trouver
    0.66
    횟
    0.65
    Activations Density 0.190%

    No Known Activations