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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12604
    Prev
    Next
    INDEX
    Explanations

    CSS properties relating to background color styling

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

    background color

    np_acts-logits-general · gemini-2.0-flash

    background color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CreateModel
    -0.75
    MigrationBuilder
    -0.66
     gyhoeddwyd
    -0.62
    FunctionFlags
    -0.58
    __(/*!
    -0.57
     OMITTED
    -0.54
     }}"></
    -0.53
    IMPORTED
    -0.51
    XtraReports
    -0.50
     ujednoznacz
    -0.49
    POSITIVE LOGITS
     background
    1.51
     Background
    1.30
    background
    1.29
     BACKGROUND
    1.21
    Background
    1.21
     backgrounds
    1.19
    BACKGROUND
    1.10
    背景
    1.09
     bg
    1.04
     achtergrond
    1.03
    Activations Density 0.295%

    No Known Activations