© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10199
    Prev
    Next
    INDEX
    Explanations

    various types of opening and closing parentheses or quotation marks in text

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

    Opening parentheses followed by various characters

    np_acts-logits-general · gemini-2.0-flash

    opening parentheses followed by code identifiers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ']))
    -0.69
    ")))
    -0.68
    "]))
    -0.68
    ')))
    -0.68
    ]')
    -0.67
     }))
    -0.67
    "))
    -0.66
    )])
    -0.66
    }})
    -0.65
    ]})
    -0.64
    POSITIVE LOGITS
    zelfde
    0.73
     raiſ
    0.68
    expandindo
    0.66
    ($
    0.65
    ('
    0.65
    __((
    0.65
    pecabe
    0.64
    (@
    0.63
     ostavi
    0.62
    ("
    0.62
    Activations Density 0.289%

    No Known Activations