© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116229
    Prev
    Next
    INDEX
    Explanations

    references to "fellow" or the notion of camaraderie and companionship among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    person in a shared group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cóc
    -0.51
     sprechen
    -0.42
     cilind
    -0.41
    HPP
    -0.41
     prazo
    -0.41
     '\\;'
    -0.41
    aarrggbb
    -0.40
     daß
    -0.40
     végét
    -0.40
    nastics
    -0.39
    POSITIVE LOGITS
     fellow
    1.24
     FELLOW
    1.03
    Fellow
    0.97
     Fellow
    0.95
    fellow
    0.86
    同じく
    0.69
     sesama
    0.66
     compatri
    0.65
     countryman
    0.64
    ellow
    0.62
    Activations Density 0.003%

    No Known Activations