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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    punctuation and closing syntax characters in code

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

    Parentheses and brackets

    np_acts-logits-general · gemini-2.0-flash

    closing parenthesis and bracket sequences

    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
     ब्रेकडाउन
    -0.79
    Tikang
    -0.79
     Administrativna
    -0.78
    LookAnd
    -0.75
     ujednoznacz
    -0.72
    出版年
    -0.72
     Infórmanos
    -0.71
    RenderAtEndOf
    -0.69
     المعيارى
    -0.69
    Portale
    -0.69
    POSITIVE LOGITS
    ))))
    0.98
    ]))
    0.97
    )))
    0.95
    )))))
    0.93
    ])))
    0.93
    ()))
    0.91
    ())))
    0.90
    ))
    0.87
    )])
    0.86
    '))
    0.84
    Activations Density 0.832%

    No Known Activations