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. 12005
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming

    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
     يتيمه
    -0.72
    requestBody
    -0.68
    Wander
    -0.66
     Srin
    -0.66
    cura
    -0.65
     Coruña
    -0.64
     $_"
    -0.64
     الحره
    -0.63
    ADM
    -0.63
     come
    -0.63
    POSITIVE LOGITS
    if
    1.41
     if
    1.38
    IF
    1.29
     IF
    1.29
     If
    1.20
     ifs
    1.18
    If
    1.14
    Nếu
    1.08
    ifs
    1.05
    elsif
    1.02
    Activations Density 0.179%

    No Known Activations