© 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. 6142
    Prev
    Next
    INDEX
    Explanations

    references to comic strip characters or creators

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

    comics or comic strips

    np_acts-logits-general · gemini-2.0-flash

    comic strips

    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
     صوتيه
    -0.69
     tournage
    -0.61
    BeginContext
    -0.57
    تقاوى
    -0.56
     MonoBehaviour
    -0.56
     filme
    -0.55
    QPalette
    -0.55
    Geplaatst
    -0.55
     CreateTagHelper
    -0.55
    abestanden
    -0.54
    POSITIVE LOGITS
     comics
    1.47
     comic
    1.38
     Comics
    1.18
    comic
    1.17
    comics
    1.16
     Comic
    1.10
    Comics
    1.05
     panel
    1.03
     panels
    1.00
    Comic
    1.00
    Activations Density 0.181%

    No Known Activations