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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15610
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural or conditional requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.85
     houſe
    -0.72
    ConstraintMaker
    -0.71
    fjspx
    -0.69
     ]
    
    -0.69
     awn
    -0.69
     cleanest
    -0.69
     LNB
    -0.68
    liothèque
    -0.68
    SerializedSize
    -0.68
    POSITIVE LOGITS
     Without
    0.70
     without
    0.69
     necessarily
    0.66
    Without
    0.64
     necesariamente
    0.61
     necessariamente
    0.59
    нологі
    0.58
    مصادر
    0.58
    HttpFoundation
    0.56
    without
    0.55
    Activations Density 0.077%

    No Known Activations