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. 18-GEMMASCOPE-RES-16K
    6. 1448
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to horses and equine activities

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

    horses or related terms

    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 @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moeite
    -0.53
    Nef
    -0.51
     citazioni
    -0.49
    catraz
    -0.48
    மி
    -0.45
    henswürdigkeiten
    -0.44
    biór
    -0.44
     rami
    -0.43
    IZONTAL
    -0.43
     Censo
    -0.43
    POSITIVE LOGITS
     horse
    1.32
     horses
    1.31
    Horses
    1.29
     Horses
    1.28
     Horse
    1.26
     HORSE
    1.21
     equine
    1.20
    horses
    1.16
    Horse
    1.15
    horse
    1.14
    Activations Density 0.215%

    No Known Activations