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. 7-GEMMASCOPE-RES-16K
    6. 15750
    Prev
    Next
    INDEX
    Explanations

    references to climate-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rubber
    -0.50
     Rubber
    -0.49
     possession
    -0.47
     goods
    -0.47
    heits
    -0.46
     orders
    -0.46
     Ouv
    -0.46
     Verder
    -0.46
     Sons
    -0.45
     Possession
    -0.45
    POSITIVE LOGITS
     climate
    2.52
    Climate
    2.30
     Climate
    2.30
     CLIMATE
    2.20
    climate
    2.20
     klima
    1.80
     Klima
    1.65
     climates
    1.64
     klimat
    1.57
    klima
    1.53
    Activations Density 0.080%

    No Known Activations