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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29201
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation and certain specific syntactical structures in programming code

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

    closing punctuation and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ק
    -0.84
    e
    -0.81
    ed
    -0.74
     Schultz
    -0.73
    gdx
    -0.71
    FilterChain
    -0.70
    ي
    -0.70
     hom
    -0.69
     Mitter
    -0.69
     Schroeder
    -0.67
    POSITIVE LOGITS
    )),
    1.31
    ]),
    1.20
    }),
    1.18
     ),
    1.12
    ],
    1.09
    .",
    1.08
    ),
    1.04
    __':
    1.04
    `,
    1.03
    '],
    1.02
    Activations Density 0.004%

    No Known Activations