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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 3424
    Prev
    Next
    INDEX
    Explanations

    words related to minimum values or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.75
    reactstrap
    -0.74
     تضيفلها
    -0.72
     velas
    -0.69
    جستارهای
    -0.69
    toHave
    -0.68
    gri
    -0.66
     CiNii
    -0.64
     byteArray
    -0.63
    Ligações
    -0.63
    POSITIVE LOGITS
     min
    2.33
    min
    2.26
     Min
    2.22
    Min
    2.15
     MIN
    2.06
    MIN
    2.00
    getMin
    1.72
     getMin
    1.68
    setMin
    1.55
     mins
    1.46
    Activations Density 0.078%

    No Known Activations