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. 2-GEMMASCOPE-RES-16K
    6. 6687
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical processes, attributes of text areas, and programming-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.89
    writeFieldEnd
    -0.83
     ExecuteAsync
    -0.68
     tslint
    -0.67
    LookAnd
    -0.66
    GraphicsUnit
    -0.65
    onOptions
    -0.64
     وتسجيلات
    -0.64
    سجيل
    -0.63
    Tikang
    -0.62
    POSITIVE LOGITS
    textarea
    0.69
    GroupLayout
    0.61
    
    0.52
     trick
    0.52
     Rück
    0.51
    occup
    0.48
    Manifest
    0.47
    inher
    0.45
    ouwen
    0.44
    Featured
    0.44
    Activations Density 2.703%

    No Known Activations