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. 7970
    Prev
    Next
    INDEX
    Explanations

    terms related to transactions involving sales and property

    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
     препратки
    -0.69
     Somit
    -0.65
    GETHER
    -0.65
     }}"></
    -0.63
    )++;
    -0.61
    ,:]
    -0.59
    μως
    -0.58
    ActionMode
    -0.58
    ).__
    -0.58
    DNEY
    -0.58
    POSITIVE LOGITS
     sell
    0.74
    LookAnd
    0.66
     Sell
    0.62
    Sell
    0.57
     sells
    0.57
     Sale
    0.54
     temperature
    0.53
     worker
    0.53
     sold
    0.53
     esclavos
    0.52
    Activations Density 0.135%

    No Known Activations