© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2985
    Prev
    Next
    INDEX
    Explanations

    terms related to equine therapy and its benefits for rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    horses and equine-assisted therapy

    np_acts-logits-general · gemini-2.0-flash

    horse and equine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     científicas
    -0.64
     supérieurs
    -0.60
     بيها
    -0.56
    pulumi
    -0.56
    WriteTagHelper
    -0.53
    "?>
    -0.53
    TintMode
    -0.53
    rrggbb
    -0.52
     grève
    -0.52
     amarillas
    -0.52
    POSITIVE LOGITS
     horse
    2.18
     horses
    2.07
     Horse
    1.85
    Horse
    1.81
     equine
    1.79
     Horses
    1.77
    horse
    1.77
     HORSE
    1.73
     equestrian
    1.71
    Horses
    1.65
    Activations Density 0.131%

    No Known Activations