Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12638
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and personal reflections related to beauty and trust

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

    sentiment or feeling

    np_acts-logits-general · gemini-2.0-flash

    descriptions of qualities

    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
    onViewCreated
    -0.70
    CloseOperation
    -0.49
    igera
    -0.48
    SourceChecksum
    -0.47
     fileSize
    -0.47
     Stamps
    -0.45
     autorytatywna
    -0.45
    ormick
    -0.44
    verwijspagina
    -0.44
     Concentr
    -0.43
    POSITIVE LOGITS
    ANSA
    0.47
     gué
    0.37
    CompilerServices
    0.35
    StoryboardSegue
    0.34
     enfans
    0.33
    __(/*!
    0.32
     nødven
    0.32
     preescolar
    0.32
     necesariamente
    0.31
     impré
    0.31
    Activations Density 0.493%

    No Known Activations