© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8153
    Prev
    Next
    INDEX
    Explanations

    mentions of "Earth"

    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
    Technologies
    -0.72
     Technologies
    -0.70
     technologies
    -0.66
     TECHNOLOGIES
    -0.65
    technologies
    -0.65
    __(/*!
    -0.64
     technological
    -0.60
     Technolog
    -0.58
    Technological
    -0.57
     technolog
    -0.56
    POSITIVE LOGITS
     earth
    1.44
    earth
    1.20
     Earth
    1.19
     EARTH
    1.16
    Earth
    1.14
    EARTH
    1.04
     earths
    0.89
     Erde
    0.76
     neutral
    0.71
     aarde
    0.71
    Activations Density 0.053%

    No Known Activations