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. 2-GEMMASCOPE-RES-16K
    6. 3575
    Prev
    Next
    INDEX
    Explanations

    mentions of various problems or topics of concern

    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
     supérieures
    -0.70
     réguli
    -0.69
     colorés
    -0.68
     démocr
    -0.68
     nationaux
    -0.67
     complètes
    -0.65
     Rebekah
    -0.64
     tombé
    -0.64
    łącz
    -0.63
     nacionales
    -0.63
    POSITIVE LOGITS
     issues
    3.77
     Issues
    3.46
    Issues
    3.37
    issues
    3.36
     issue
    3.14
     ISSUES
    3.09
    issue
    2.87
     Issue
    2.79
    Issue
    2.77
    ISSUES
    2.72
    Activations Density 0.083%

    No Known Activations