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. 5-GEMMASCOPE-RES-16K
    6. 2541
    Prev
    Next
    INDEX
    Explanations

    programming-related structure and object keywords

    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
    tagHelperRunner
    -1.36
    ValueStyle
    -1.31
     CreateTagHelper
    -1.11
     nahilalakip
    -1.03
     gynhyrchwyd
    -0.94
    TagHelpers
    -0.93
    ')")
    -0.90
    AccessorTable
    -0.90
    ResumeLayout
    -0.90
    '},
    
    -0.89
    POSITIVE LOGITS
    "
    0.87
    </i>
    0.76
    ”
    0.73
     ‚
    0.64
    ",
    0.63
    \"
    0.62
    ."
    0.62
     [
    0.62
    </em>
    0.61
    ".
    0.60
    Activations Density 1.744%

    No Known Activations