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. 2-GEMMASCOPE-RES-16K
    6. 6268
    Prev
    Next
    INDEX
    Explanations

    pieces of code related to function definitions and conditionals in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.54
    anka
    -0.51
    \}\\
    -0.50
    ribadian
    -0.50
    ective
    -0.49
    حوالہ
    -0.49
     supplemented
    -0.49
    --]
    -0.49
    GPP
    -0.48
    enheim
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.68
     AssemblyCompany
    0.67
    ьаж
    0.59
     lccn
    0.59
    かわらず
    0.59
     تضيفلها
    0.58
    TagMode
    0.56
     SwitchCompat
    0.55
    abinieri
    0.54
     Réponses
    0.53
    Activations Density 0.215%

    No Known Activations