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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 7304
    Prev
    Next
    INDEX
    Explanations

    conditional statements and block delimiters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.61
    CRETE
    -0.57
    ViewFeatures
    -0.57
    ereich
    -0.54
    Chham
    -0.54
    .*")]
    -0.53
    =\""
    -0.50
    änglich
    -0.49
    Romain
    -0.49
    әне
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.69
    AndroidJUnit
    0.65
    ymce
    0.64
    apollo
    0.62
    Gambas
    0.61
    tableFuture
    0.59
    曖昧さ回避
    0.59
    dehy
    0.58
     Мексичка
    0.57
     dair
    0.57
    Activations Density 0.101%

    No Known Activations