© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7287
    Prev
    Next
    INDEX
    Explanations

    pronouns and phrases indicating the presence of someone needing assistance or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.64
    styleType
    -0.61
    setVerticalGroup
    -0.57
    Datuak
    -0.52
    fitriones
    -0.50
     TextAppearance
    -0.49
    stateProvider
    -0.48
     BoxFit
    -0.48
     onOptions
    -0.48
    UnknownFieldSet
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.61
     icmp
    0.36
    rax
    0.36
    jgl
    0.35
    ={()=>
    0.35
     nod
    0.35
    Sonic
    0.34
    YMMV
    0.34
    mpg
    0.34
    Slick
    0.33
    Activations Density 0.051%

    No Known Activations