© 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. 20-GEMMASCOPE-RES-16K
    11. 273
    Prev
    Next
    INDEX
    Explanations

    specific dimensions and attributes related to images or graphics

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

    Image dimensions or resolutions

    np_acts-logits-general · gemini-2.0-flash

    dimensions like 150x150

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    WebVitals
    -0.94
    awtextra
    -0.89
     '\\;'
    -0.89
     TestBed
    -0.89
     CreateTagHelper
    -0.84
    GraphicsUnit
    -0.81
    ⓧ
    -0.78
    Hentet
    -0.75
     BorderRadius
    -0.75
     estekak
    -0.74
    POSITIVE LOGITS
     auto
    0.52
     становника
    0.46
    каун
    0.46
    ğunu
    0.45
    auto
    0.44
    ExecutionContext
    0.43
     schre
    0.42
     whistle
    0.42
    usercontent
    0.40
     بك
    0.40
    Activations Density 0.178%

    No Known Activations