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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12071
    Prev
    Next
    INDEX
    Explanations

    function declarations and their corresponding blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     named
    -0.53
     background
    -0.48
    ICZ
    -0.48
    ByName
    -0.47
    ίας
    -0.47
     dynamo
    -0.46
     investigated
    -0.45
     getField
    -0.45
    ARDS
    -0.45
    ツリー
    -0.45
    POSITIVE LOGITS
    __':
    
    1.08
    __':
    1.06
    StoryboardSegue
    1.05
     ModelExpression
    1.01
    __":
    0.98
     AssemblyProduct
    0.92
    AndEndTag
    0.90
     NSCoder
    0.89
    ViewFeatures
    0.89
    saraba
    0.87
    Activations Density 0.042%

    No Known Activations