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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8837
    Prev
    Next
    INDEX
    Explanations

    the names of large animals.

    oai_token-act-pair · gemini-1.5-flashTriggered by @rka87338

    animals and animal-related terms

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

    Animal names

    np_acts-logits-general · gemini-2.0-flash

    animals followed by descriptions or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.55
    /**
    -0.50
    setItem
    -0.47
    lors
    -0.46
    ICED
    -0.44
    handa
    -0.44
     Entdecken
    -0.42
     العنوان
    -0.42
     senjata
    -0.41
    vda
    -0.41
    POSITIVE LOGITS
     Савезне
    0.70
     mascot
    0.69
    pox
    0.68
    IUrlHelper
    0.67
     species
    0.67
    出版年
    0.65
     breed
    0.65
    complexContent
    0.65
    djangoproject
    0.65
     PhpStorm
    0.65
    Activations Density 0.370%

    No Known Activations