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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5115
    Prev
    Next
    INDEX
    Explanations

    procedure and instructions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.71
     Auge
    -0.53
    enus
    -0.52
     Entdecke
    -0.51
     versucht
    -0.46
    fscanf
    -0.45
    ⓧ
    -0.45
     questioned
    -0.45
    CommandHandler
    -0.45
    είο
    -0.44
    POSITIVE LOGITS
     simply
    1.90
    simply
    1.78
    Simply
    1.77
     Simply
    1.66
     simplemente
    1.48
     einfach
    1.48
     semplicemente
    1.40
     simplement
    1.34
     просто
    1.29
     Simplemente
    1.27
    Activations Density 0.558%

    No Known Activations