© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3088
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions

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

    mathematical notation and technical formulas, especially those involving Greek letters and mathematical symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    }}}}
    -0.75
    }}}
    -0.62
    ]})
    -0.61
     }}}
    -0.59
    )})
    -0.57
    }}-
    -0.56
    }}+
    -0.56
    ])))
    -0.56
    ())))
    -0.56
    }}-\
    -0.55
    POSITIVE LOGITS
    _{[
    0.80
    хьтан
    0.78
    _{(
    0.63
    multirow
    0.58
     Baran
    0.55
     SLC
    0.54
    vius
    0.52
    _{-\
    0.51
    onAttach
    0.50
    ⓧ
    0.50
    Activations Density 1.137%

    No Known Activations