© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6508
    Prev
    Next
    INDEX
    Explanations

    responses associated with answers to questions, particularly structured answers and explanations

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

    "Answer" or related foreign-language terms

    np_acts-logits-general · gemini-2.0-flash

    answer or solution

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Personensuche
    -0.49
     }}^{
    -0.36
    OneToMany
    -0.35
    TagHelper
    -0.35
     charge
    -0.35
     FontAwesome
    -0.34
     semin
    -0.34
    FontAwesome
    -0.34
     tagName
    -0.33
    transQ
    -0.33
    POSITIVE LOGITS
     answer
    0.78
     oplossing
    0.77
    answer
    0.74
     solución
    0.69
     Lösung
    0.69
    solution
    0.69
     soluciones
    0.69
    Lösung
    0.68
    Solution
    0.68
    ösungen
    0.68
    Activations Density 0.598%

    No Known Activations