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. 0-GEMMASCOPE-RES-16K
    6. 229
    Prev
    Next
    INDEX
    Explanations

    references to the act of collecting information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.66
    клопе
    -0.64
    jmniej
    -0.63
    SPATH
    -0.63
     Pyrr
    -0.62
     endometri
    -0.56
     neceſſ
    -0.55
     dataSnapshot
    -0.55
     inſ
    -0.54
     itſelf
    -0.52
    POSITIVE LOGITS
     collect
    0.80
     collected
    0.73
    océ
    0.62
    collected
    0.60
     collecting
    0.60
     select
    0.59
    deln
    0.59
     sto
    0.56
    INTAIN
    0.56
     //$
    0.56
    Activations Density 0.163%

    No Known Activations