© 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. 10183
    Prev
    Next
    INDEX
    Explanations

    references to wildlife conservation and endangered species

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

    near animals or scientific studies

    np_acts-logits-general · gemini-2.0-flash

    wildlife and animals

    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
     initComponents
    -0.60
    SourceChecksum
    -0.58
    awtextra
    -0.56
    AddHtmlAttribute
    -0.55
    ($__
    -0.53
     kaynağından
    -0.48
    ContentAsync
    -0.48
    IsContent
    -0.47
    (!__
    -0.46
    GeneratedMessage
    -0.44
    POSITIVE LOGITS
     animal
    1.85
     animals
    1.65
     wildlife
    1.61
    animal
    1.58
     Animal
    1.57
     zoo
    1.53
    Animal
    1.52
     ANIMAL
    1.45
     Animals
    1.43
     Wildlife
    1.41
    Activations Density 0.377%

    No Known Activations