© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10520
    Prev
    Next
    INDEX
    Explanations

    discussions around the effectiveness and evaluation of communication and relationships

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

    something is not right or failing

    np_acts-logits-general · gemini-2.0-flash

    negative outcomes or failures

    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
    UrlResolution
    -0.50
     AppCompatTheme
    -0.48
     quitté
    -0.47
    ựu
    -0.41
     truy
    -0.41
     okol
    -0.41
     strade
    -0.41
     combinatie
    -0.41
    rolid
    -0.41
     forbindelse
    -0.40
    POSITIVE LOGITS
     unsatisfactory
    1.32
     failures
    1.25
     incorrect
    1.23
     failure
    1.21
     disappointing
    1.18
     inadequate
    1.18
     failed
    1.17
     wrong
    1.15
     failing
    1.14
     faulty
    1.11
    Activations Density 1.420%

    No Known Activations