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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 15164
    Prev
    Next
    INDEX
    Explanations

    conditional statements and function calls within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    涯
    -0.58
    kapet
    -0.56
    PageContext
    -0.54
     Roskov
    -0.54
    BASEPATH
    -0.52
     reloadData
    -0.52
     Kleid
    -0.52
     soloist
    -0.51
    spesies
    -0.51
    sizeCache
    -0.51
    POSITIVE LOGITS
    equalsIgnoreCase
    0.83
    equals
    0.78
    System
    0.57
    content
    0.54
     externi
    0.53
     intptr
    0.50
    ního
    0.50
     isEqualToString
    0.49
     esternos
    0.49
     content
    0.49
    Activations Density 0.069%

    No Known Activations