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. 15774
    Prev
    Next
    INDEX
    Explanations

    references to skincare products and treatments for acne

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

    preceding explanations, updates, or details

    np_acts-logits-general · gemini-2.0-flash

    information seeking and advice

    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
     (
    -0.63
    unlikely
    -0.55
     however
    -0.54
     (
    -0.52
     However
    -0.52
    However
    -0.51
     unlikely
    -0.50
     Cohen
    -0.50
     —
    -0.49
    fisk
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    1.16
    Personendaten
    0.98
     propOrder
    0.95
    Sucesor
    0.88
    LookAnd
    0.80
    protoimpl
    0.79
     للاسماء
    0.79
    حوالہ
    0.77
    rungsseite
    0.77
    évaluateur
    0.75
    Activations Density 0.112%

    No Known Activations