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. 20-GEMMASCOPE-RES-16K
    6. 14327
    Prev
    Next
    INDEX
    Explanations

    specific financial terms and conditions related to options and contracts

    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
    IntentFilter
    -0.81
    TypedDataSet
    -0.69
    awtextra
    -0.67
     Normdatei
    -0.60
    WireFormatLite
    -0.59
     disponibilités
    -0.59
     مرئيه
    -0.58
     BorderSide
    -0.58
    المكان
    -0.57
     rappro
    -0.56
    POSITIVE LOGITS
     option
    1.93
     Option
    1.75
    option
    1.74
     options
    1.68
    Option
    1.64
    options
    1.52
     OPTION
    1.49
     Options
    1.49
    OPTION
    1.43
    Options
    1.39
    Activations Density 0.251%

    No Known Activations