© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 50230
    Prev
    Next
    INDEX
    Explanations

    phrases related to pouring and transferring liquids

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

    pouring and filling

    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
    olism
    -0.50
    Ego
    -0.50
    umel
    -0.50
     pinulongan
    -0.50
    VPB
    -0.49
    braio
    -0.48
    ressum
    -0.48
    igare
    -0.47
    Bol
    -0.47
    Executive
    -0.47
    POSITIVE LOGITS
     pouring
    0.43
     derra
    0.39
    tvguidetime
    0.39
     pour
    0.38
     líquido
    0.37
    pour
    0.35
     Pour
    0.34
    astify
    0.34
     poured
    0.33
     remplissage
    0.33
    Activations Density 0.031%

    No Known Activations