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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8644
    Prev
    Next
    INDEX
    Explanations

    terms related to invasion and its various forms and uses in contexts such as biology, ecology, and social phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.52
     <<<<<<<<<<<<<<
    -0.48
    internalType
    -0.46
     dessen
    -0.45
    ircut
    -0.44
    licka
    -0.44
     couteau
    -0.42
    arschu
    -0.42
     Byr
    -0.42
    orological
    -0.42
    POSITIVE LOGITS
     invasion
    1.07
     invade
    0.94
     Invasion
    0.90
    invasion
    0.89
     eco
    0.89
    Invasion
    0.88
     invasive
    0.86
     invaded
    0.86
     invasions
    0.85
     penetration
    0.82
    Activations Density 0.137%

    No Known Activations