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. 5-GEMMASCOPE-RES-16K
    6. 16130
    Prev
    Next
    INDEX
    Explanations

    phrases indicating arrival or presence at a location or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$((
    -0.66
    flashdata
    -0.63
    MMdd
    -0.59
    readAs
    -0.59
    اریخ
    -0.57
     AVE
    -0.56
    berte
    -0.55
    CreateModel
    -0.55
     position
    -0.55
     communication
    -0.54
    POSITIVE LOGITS
     turnout
    1.02
    сшта
    0.67
    wakeup
    0.66
     Tune
    0.66
    chtigkeit
    0.66
     tuning
    0.65
    úblico
    0.65
     democrá
    0.65
    Lumin
    0.64
     Lumin
    0.64
    Activations Density 0.056%

    No Known Activations