© 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. 117080
    Prev
    Next
    INDEX
    Explanations

    terms related to electrodes and devices, particularly focusing on cathodes and related terms

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

    cathode, Catherine, catheter, catastrophe

    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
    ◆◇
    -0.49
    AnchorStyles
    -0.48
     estekak
    -0.47
    EDEFAULT
    -0.46
    ||}
    -0.46
    %
    
    -0.45
    --
    
    -0.44
     agre
    -0.44
    :--
    -0.43
    jsxFileName
    -0.43
    POSITIVE LOGITS
     Cat
    0.76
     Cater
    0.73
    Cat
    0.71
     Caterina
    0.70
     Katz
    0.70
     Catharine
    0.68
    ATHERINE
    0.68
     Cate
    0.68
    aterina
    0.68
     Catalina
    0.67
    Activations Density 0.017%

    No Known Activations