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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4932
    Prev
    Next
    INDEX
    Explanations

    elements that highlight cultural diversity and fusion

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

    Following "more" or other degree words

    np_acts-logits-general · gemini-2.0-flash

    describing styles or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kijken
    -0.67
    esgue
    -0.65
     forfatter
    -0.63
     ulang
    -0.62
    autant
    -0.61
     puta
    -0.59
     meilleures
    -0.59
    swick
    -0.58
     particulière
    -0.58
     térmico
    -0.57
    POSITIVE LOGITS
     edgy
    0.82
     softer
    0.80
     aggressive
    0.79
     traditional
    0.79
     sporty
    0.78
     austere
    0.77
     earthy
    0.77
     gritty
    0.74
     modern
    0.72
     somber
    0.71
    Activations Density 0.377%

    No Known Activations