© 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. 33-GEMMASCOPE-RES-16K
    11. 2061
    Prev
    Next
    INDEX
    Explanations

    elements related to adjacency and connections in spatial or structural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autorest
    -0.52
    AddTagHelper
    -0.43
     mijne
    -0.41
    paksa
    -0.41
    istoitu
    -0.41
     utafitiHapana
    -0.40
     Einzelnen
    -0.39
    awtextra
    -0.38
    setScene
    -0.37
    uarkan
    -0.36
    POSITIVE LOGITS
     neighboring
    3.09
     neighbouring
    3.02
     nearby
    2.98
     adjacent
    2.83
     adjoining
    2.56
    nearby
    2.45
     Nearby
    2.42
     surrounding
    2.41
     Adjacent
    2.38
    Nearby
    2.30
    Activations Density 1.034%

    No Known Activations