Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 917
    Prev
    Next
    INDEX
    Explanations

    arguments against government policies and actions regarding social issues

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

    modal verbs and auxiliaries

    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
    ')))
    -0.37
    ")(
    -0.36
    ]));
    
    -0.36
    )}</
    -0.36
    }))
    
    -0.35
    Pyx
    -0.34
    ")));
    
    -0.34
    ToSend
    -0.34
     보기
    -0.33
    "))
    
    -0.32
    POSITIVE LOGITS
    SharedDtor
    0.62
     للاسماء
    0.58
    richTextPanel
    0.49
     utafitiHapana
    0.49
     تضيفلها
    0.46
    ntax
    0.45
     betweenstory
    0.44
    ElementException
    0.44
    tanleria
    0.44
    存于互联网档案馆
    0.43
    Activations Density 0.092%

    No Known Activations