© 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. 29213
    Prev
    Next
    INDEX
    Explanations

    nested parentheses and their structures in coding or mathematical expressions

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

    numbers followed by code or symbols

    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
    "]}
    -0.63
    ]>
    -0.58
    ]))
    -0.56
    )\}
    -0.53
    ))){
    -0.53
    ...]
    -0.53
    )))
    -0.53
    }]$
    -0.51
    "]);
    -0.51
     cé
    -0.51
    POSITIVE LOGITS
    WireFormatLite
    0.91
     Alembic
    0.83
     MessageBoxIcon
    0.81
    openzeppelin
    0.78
    脚注の使い方
    0.75
    flashdata
    0.75
    ImageContext
    0.75
    ValueStyle
    0.74
    providedIn
    0.73
     NgModule
    0.73
    Activations Density 0.009%

    No Known Activations