Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12054
    Prev
    Next
    INDEX
    Explanations

    information related to dog care and training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dogs
    -0.58
     Dogs
    -0.55
    dogs
    -0.55
     animales
    -0.55
     animals
    -0.54
     animais
    -0.53
     soutenir
    -0.53
     djur
    -0.53
    animals
    -0.53
     animal
    -0.53
    POSITIVE LOGITS
     kasarigan
    1.06
     cage
    0.88
    ArrowToggle
    0.83
    FieldBuilder
    0.81
     exercise
    0.81
     crate
    0.78
     enrichment
    0.74
     Enrichment
    0.74
     playtime
    0.74
    cage
    0.73
    Activations Density 0.147%

    No Known Activations