© 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. 23-GEMMASCOPE-RES-16K
    11. 11999
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying and believing in particular groups or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     if
    -0.47
    if
    -0.41
     again
    -0.38
    be
    -0.35
    let
    -0.35
    un
    -0.35
     some
    -0.34
    dAtA
    -0.34
     when
    -0.34
     onCreateView
    -0.33
    POSITIVE LOGITS
     którzy
    0.76
     kteří
    0.71
     queſta
    0.70
     ktorí
    0.69
    ſelves
    0.69
     ſind
    0.68
     Houſe
    0.67
    VYMaps
    0.67
     themſelves
    0.66
     Verſ
    0.65
    Activations Density 0.622%

    No Known Activations