© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2543
    Prev
    Next
    INDEX
    Explanations

    references to Pacific Island cultures

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

    "Pas" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    Pas followed by specific words

    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
    ChildScrollView
    -0.86
     Económica
    -0.69
    ValueGenerated
    -0.62
    دانشنامهٔ
    -0.62
     wireType
    -0.61
    Према
    -0.58
    Cyfarwyddwr
    -0.58
    brigens
    -0.58
    ViewFeatures
    -0.57
     kaarangay
    -0.57
    POSITIVE LOGITS
     Pas
    0.97
    Pas
    0.88
     PASS
    0.78
     Pass
    0.74
     PAS
    0.73
     tense
    0.71
    PASS
    0.70
     Pase
    0.69
    pas
    0.69
    tvguidetime
    0.68
    Activations Density 0.218%

    No Known Activations