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. 1933
    Prev
    Next
    INDEX
    Explanations

    specific references to horses and related management practices

    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
     Jamaica
    -0.81
    Jamaica
    -0.79
     Lagos
    -0.74
     Brooklyn
    -0.71
     Jamaican
    -0.70
    #+#
    -0.70
     Philadelphia
    -0.70
     Philly
    -0.68
     Liverpool
    -0.65
    Philadelphia
    -0.65
    POSITIVE LOGITS
     Idaho
    1.71
    Idaho
    1.54
     Montana
    1.51
    Montana
    1.41
     Boise
    1.36
     Missoula
    1.32
     Wyoming
    1.26
     Coeur
    1.19
     Yellowstone
    1.17
    Wyoming
    1.16
    Activations Density 0.546%

    No Known Activations