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. 1189
    Prev
    Next
    INDEX
    Explanations

    programming function definitions

    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
     يتيمه
    -1.19
     nahilalakip
    -0.99
    ^(@)
    -0.98
     ***/
    -0.87
    IonicModule
    -0.83
    webElementXpaths
    -0.83
    KommentareTeilen
    -0.82
    AnchorStyles
    -0.80
     NUKAT
    -0.79
    --
    
    -0.77
    POSITIVE LOGITS
    Def
    2.19
    def
    2.17
     Def
    2.13
     def
    2.11
    DEF
    1.84
     DEF
    1.74
    defs
    1.48
    Defs
    1.47
     déf
    1.31
     deflation
    1.11
    Activations Density 0.089%

    No Known Activations