© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 73974
    Prev
    Next
    INDEX
    Explanations

    references and characteristics related to the Earth and its atmosphere

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

    Earth's physical characteristics and rotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    __(/*!
    -0.68
     ProtoMessage
    -0.65
    rungsseite
    -0.57
     ligiloj
    -0.54
     invokingState
    -0.52
    oa̍t
    -0.52
    lecular
    -0.51
    verifyException
    -0.48
    ACIAS
    -0.47
    propylene
    -0.47
    POSITIVE LOGITS
     Earth
    0.66
    Earth
    0.63
     Majefty
    0.59
     earth
    0.58
     aarde
    0.52
    earth
    0.50
     planète
    0.49
     ſtate
    0.49
     地球
    0.48
     EARTH
    0.47
    Activations Density 0.017%

    No Known Activations