© 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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10948
    Prev
    Next
    INDEX
    Explanations

    patterns and symbols typical in mathematical notation and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])))
    -0.38
    }],
    -0.30
     tagli
    -0.29
    })`
    -0.29
    wechsel
    -0.28
    BibitemShut
    -0.28
    ]))
    -0.27
    $
    -0.27
     variations
    -0.27
     corpi
    -0.27
    POSITIVE LOGITS
    zzlies
    0.68
     nakalista
    0.68
    msgTypes
    0.66
    UnusedPrivate
    0.63
    awtextra
    0.59
    Derp
    0.59
    তথ্যসূত্র
    0.59
    ACHUSET
    0.57
     createSlice
    0.57
    RTGC
    0.55
    Activations Density 1.485%

    No Known Activations