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. 8-GEMMASCOPE-RES-16K
    6. 4010
    Prev
    Next
    INDEX
    Explanations

    references to various forms and aspects of training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edd
    -0.83
     Osbourne
    -0.83
     Antara
    -0.82
     KeyCode
    -0.79
     écl
    -0.75
     Diocese
    -0.75
     Automobiles
    -0.72
    poc
    -0.71
     Sedgwick
    -0.71
     Necklace
    -0.70
    POSITIVE LOGITS
     training
    1.36
     Training
    1.14
     trainings
    1.12
    Training
    1.08
    training
    1.08
     train
    1.05
     trainers
    1.04
     TRAINING
    1.00
     Trainings
    0.99
    TRAINING
    0.99
    Activations Density 0.069%

    No Known Activations