© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    instances of consideration, exploration, and planning related to various subjects

    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
     disambiguazione
    -0.52
    Personendaten
    -0.49
     kasarigan
    -0.46
    ۜ
    -0.43
    ніципа
    -0.42
    PreExecute
    -0.41
     jugement
    -0.41
    MessageTagHelper
    -0.40
     iprot
    -0.40
     strijd
    -0.38
    POSITIVE LOGITS
     possibility
    0.97
     possibilities
    0.96
     options
    0.91
     Possibilities
    0.82
     option
    0.81
    possibility
    0.81
     possibilidade
    0.79
    options
    0.79
     posibilidad
    0.79
     alternatives
    0.79
    Activations Density 0.347%

    No Known Activations