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. 17-GEMMASCOPE-RES-16K
    6. 5831
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or patterns of whitespace and/or indentation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.59
    お楽しみに
    -0.57
    Itoa
    -0.54
     doInBackground
    -0.54
     getResources
    -0.53
    =$?
    -0.52
     /\.(
    -0.50
    ↵↵
    -0.50
    Abitanti
    -0.48
     endforeach
    -0.48
    POSITIVE LOGITS
    Disliked
    0.66
    tagez
    0.66
     ModelExpression
    0.65
     découver
    0.65
     autorytatywna
    0.63
     Савезне
    0.61
    SourceChecksum
    0.61
     MyBatis
    0.60
    互联网档案馆
    0.58
     版本
    0.58
    Activations Density 0.073%

    No Known Activations