© 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. 29846
    Prev
    Next
    INDEX
    Explanations

    the name "Sarai" in various contexts

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

    Sarai, Sarcoma

    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
    NamedQueries
    -0.89
     Jolie
    -0.78
    ]]
    -0.73
    endsection
    -0.73
    ()]
    -0.72
    OkHttpClient
    -0.72
    ]$}
    -0.70
    rophoresis
    -0.69
    akujem
    -0.69
    </table>
    -0.68
    POSITIVE LOGITS
    AndEndTag
    0.90
    Sar
    0.84
     Sar
    0.81
     sar
    0.79
     Dupont
    0.76
    Alfonso
    0.71
    quint
    0.71
     Harrison
    0.71
     Lucre
    0.69
     useDispatch
    0.68
    Activations Density 0.023%

    No Known Activations