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. 23-GEMMASCOPE-RES-16K
    6. 5810
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to quantum mechanics and mathematical properties of physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.76
    évaluateur
    -0.60
     []:
    -0.60
    ItemBackground
    -0.57
     Préférences
    -0.56
    χή
    -0.56
    contentLoaded
    -0.53
    Diwedd
    -0.52
     تانيه
    -0.52
     kaarangay
    -0.52
    POSITIVE LOGITS
     energy
    0.80
     energies
    0.78
     momentum
    0.74
    Energy
    0.73
     Energy
    0.71
    Ener
    0.68
    energy
    0.68
     Momentum
    0.67
     Ener
    0.66
     momenta
    0.65
    Activations Density 1.264%

    No Known Activations