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. 3123
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and appliances like dishwashers

    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
    HasForeignKey
    -0.51
     Tob
    -0.47
    Xar
    -0.46
    خی
    -0.45
    attendre
    -0.43
    ůž
    -0.43
     chociaż
    -0.43
    vriende
    -0.42
     maduro
    -0.42
    parseColor
    -0.42
    POSITIVE LOGITS
    دانشنامهٔ
    0.88
    DoubleQuotes
    0.88
     Италијани
    0.83
    зулта
    0.79
    SourceChecksum
    0.74
    Dishwasher
    0.72
     dishwasher
    0.70
    principalTable
    0.70
    hbase
    0.67
    WebVitals
    0.67
    Activations Density 1.571%

    No Known Activations