© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9446
    Prev
    Next
    INDEX
    Explanations

    references to neutrality in various contexts

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

    "Neutral" and neutrality, often in publisher's notes

    np_acts-logits-general · gemini-2.0-flash

    neutral or neutrality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.55
    はじめに
    -0.50
    $")
    -0.50
    atorics
    -0.50
     getApp
    -0.50
    هرست
    -0.48
    ../../../
    -0.48
    EnableWeb
    -0.46
     MyApp
    -0.45
     للاسماء
    -0.45
    POSITIVE LOGITS
     neutral
    2.27
    neutral
    2.11
     Neutral
    2.09
    Neutral
    2.08
     neutrality
    1.86
     нейтра
    1.84
     neutre
    1.77
    UTRAL
    1.63
     neutrals
    1.60
     neutr
    1.52
    Activations Density 0.233%

    No Known Activations