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. 21-GEMMASCOPE-RES-16K
    6. 14262
    Prev
    Next
    INDEX
    Explanations

    references to specific breeds and lineage in the context of animal husbandry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penderita
    -0.45
    eseorang
    -0.45
    entration
    -0.45
    Cpp
    -0.44
    iarkan
    -0.43
    Provision
    -0.42
     RequestMethod
    -0.42
     geholfen
    -0.42
     commute
    -0.42
    سته
    -0.42
    POSITIVE LOGITS
    AddHtmlAttribute
    0.83
     bred
    0.73
     transfieras
    0.70
    
    0.69
    bred
    0.69
    Ekster
    0.66
     dam
    0.63
     sire
    0.61
     breeding
    0.60
     Cassini
    0.58
    Activations Density 0.040%

    No Known Activations