© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5735
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific method calls or property accesses in code, particularly those related to handling multipart data and file uploads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.75
    </b>
    -0.72
     
    -0.65
     (
    -0.64
     ,
    -0.62
    '
    -0.62
    <b>
    -0.61
     \
    -0.61
    ]
    -0.61
    <i>
    -0.60
    POSITIVE LOGITS
    ._
    1.84
    ]._
    1.45
     pleaſure
    1.33
     myſelf
    1.32
     purpoſe
    1.30
     Reſ
    1.27
     houſe
    1.24
     Inſ
    1.23
     Conſ
    1.23
     ſtate
    1.21
    Activations Density 0.070%

    No Known Activations