© 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. 2-GEMMASCOPE-RES-16K
    11. 15109
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.48
    ↵
    -0.40
    2
    -0.38
    '
    -0.36
    ™
    -0.34
    ,
    -0.34
    1
    -0.33
    </b>
    -0.32
     }^{
    -0.32
    ™.
    -0.32
    POSITIVE LOGITS
     EconPapers
    0.81
    AddTagHelper
    0.72
     kasarigan
    0.72
    IntoConstraints
    0.69
     الحره
    0.69
    AndEndTag
    0.68
    addContainerGap
    0.65
     GenerationType
    0.63
     laſſen
    0.62
     müſſen
    0.60
    Activations Density 0.942%

    No Known Activations