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. 10-GEMMASCOPE-RES-16K
    6. 11831
    Prev
    Next
    INDEX
    Explanations

    the presence of periods or decimal points in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.95
    complexContent
    -0.90
    mybatisplus
    -0.89
    /***/
    -0.86
     חיצוניים
    -0.86
     дописавши
    -0.85
    Hochspringen
    -0.84
     AssemblyTitle
    -0.82
    gway
    -0.82
    Hauptartikel
    -0.79
    POSITIVE LOGITS
    (.
    0.70
    ("%.
    0.69
    =.
    0.68
    0
    0.68
     /\.
    0.68
     
    0.65
     (.
    0.62
    economia
    0.62
    cancellation
    0.60
     Aron
    0.59
    Activations Density 0.272%

    No Known Activations