© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 10598
    Prev
    Next
    INDEX
    Explanations

    closing braces and related symbols in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.73
     LCCN
    -0.65
    ment
    -0.63
     doInBackground
    -0.63
    crip
    -0.63
     Boeh
    -0.62
    databind
    -0.61
    Nah
    -0.60
    kol
    -0.60
    vish
    -0.59
    POSITIVE LOGITS
    "]}
    1.30
    )})
    1.18
    ']}
    1.10
    )\}
    1.10
    .)}
    1.09
    </table>
    1.08
    '}
    1.06
    }))
    1.04
     referenties
    1.03
    ]})
    1.02
    Activations Density 0.023%

    No Known Activations