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. 25-GEMMASCOPE-RES-16K
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to CNN operations and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.63
     AttributeSet
    -0.60
    TestingModule
    -0.55
    }{*}{
    -0.53
    uerre
    -0.52
     NavController
    -0.51
     Maude
    -0.50
    Cryptography
    -0.50
    Predecesor
    -0.50
    uscular
    -0.50
    POSITIVE LOGITS
     boxes
    0.84
     Boxes
    0.78
     box
    0.76
    boxes
    0.76
    Boxes
    0.73
     detection
    0.71
     detections
    0.68
     bounding
    0.68
     Detection
    0.68
    box
    0.67
    Activations Density 0.488%

    No Known Activations