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. 10-GEMMASCOPE-RES-16K
    6. 3474
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     done
    -0.45
     parto
    -0.44
     people
    -0.42
    :
    -0.42
    ila
    -0.41
     part
    -0.41
    tire
    -0.41
     externos
    -0.40
     individuals
    -0.40
    aks
    -0.39
    POSITIVE LOGITS
    VersionUID
    0.93
    apunov
    0.92
    expandindo
    0.92
    TagMode
    0.90
    MLLoader
    0.87
    Демографія
    0.83
    NameInMap
    0.83
    twimg
    0.81
    StoryboardSegue
    0.79
     transfieras
    0.76
    Activations Density 0.124%

    No Known Activations