© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9609
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or references that affirm a point or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwitchCompat
    -0.55
     inalámb
    -0.54
    SharedDtor
    -0.53
    EndGlobal
    -0.53
     acondicion
    -0.53
     inalámbrica
    -0.52
    rungsseite
    -0.52
    ſelves
    -0.51
     Италијани
    -0.51
     fondateur
    -0.50
    POSITIVE LOGITS
     لينك
    0.51
     what
    0.44
     fe
    0.43
     gì
    0.42
     wat
    0.42
    jsonwebtoken
    0.42
    URIComponent
    0.39
     ideal
    0.37
    DateTimeField
    0.37
     quanto
    0.35
    Activations Density 0.139%

    No Known Activations