© 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. 10869
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lined" and related verbs indicating organization or structuring

    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
     fragment
    -0.58
     isabel
    -0.57
     object
    -0.53
     MonoBehaviour
    -0.51
     ordinary
    -0.51
     conv
    -0.50
     scar
    -0.50
     lele
    -0.49
     pron
    -0.49
     consig
    -0.49
    POSITIVE LOGITS
     teamed
    1.02
     billed
    0.98
     geared
    0.93
     tasked
    0.91
     slated
    0.91
     spearheaded
    0.90
     lined
    0.88
     maxed
    0.87
     poised
    0.87
     clocked
    0.86
    Activations Density 0.355%

    No Known Activations