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. 4625
    Prev
    Next
    INDEX
    Explanations

    computational terms and programming logic

    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
     AttributeSet
    -0.78
    بوابة
    -0.74
    ()]
    
    -0.69
    atchi
    -0.69
    IVEREF
    -0.67
    addPreferredGap
    -0.65
    expandindo
    -0.65
    انجليز
    -0.64
    addCriterion
    -0.63
     eventdata
    -0.62
    POSITIVE LOGITS
    XtraEditors
    0.62
    émie
    0.47
     ó
    0.44
    وضوع
    0.42
    <bos>
    0.41
    thora
    0.40
     met
    0.39
     ace
    0.39
    Copia
    0.39
     ê
    0.39
    Activations Density 0.332%

    No Known Activations