© 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. 31-GEMMASCOPE-RES-16K
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    information related to water systems and their environmental impact

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

    water infrastructure terms like "dam", "reservoir", and "river" in geographic or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and phrases related to dams, reservoirs, and water infrastructure projects.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.49
     виправивши
    -0.45
    addGap
    -0.38
    ----</
    -0.37
    addContainerGap
    -0.35
     AppCompatTheme
    -0.35
    AndEndTag
    -0.34
    addProperty
    -0.33
     Lightboxes
    -0.31
     sweaty
    -0.31
    POSITIVE LOGITS
     dams
    1.41
     dam
    1.39
     Dams
    1.14
    dams
    1.09
     hydroelectric
    1.05
     Dam
    1.03
     hydropower
    1.02
    Dam
    0.98
    dam
    0.98
     reservoir
    0.94
    Activations Density 0.158%

    No Known Activations