© 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. 35-GEMMASCOPE-RES-16K
    11. 7463
    Prev
    Next
    INDEX
    Explanations

    references to sensitivity and risk factors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.59
    ValueStyle
    -0.57
    parsedMessage
    -0.56
    tonode
    -0.47
    poir
    -0.47
    Xaml
    -0.47
     disambiguazione
    -0.47
    InsertCommand
    -0.47
    RTCF
    -0.46
    ffions
    -0.46
    POSITIVE LOGITS
     sensitive
    2.78
     sensitivity
    2.52
     Sensitive
    2.42
    sensitive
    2.36
    Sensitive
    2.28
     Sensitivity
    2.25
    sensitivity
    2.13
     sensitivities
    2.11
    Sensitivity
    2.06
     vulnerable
    2.03
    Activations Density 1.223%

    No Known Activations