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. 10957
    Prev
    Next
    INDEX
    Explanations

    references to dry conditions or states

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

    Occurrence of "dry" or "wet"

    np_acts-logits-general · gemini-2.0-flash

    dry goods, bulk goods, fruit, fertilizers

    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
     poveznice
    -0.86
     estimés
    -0.86
    StoryboardSegue
    -0.76
    QMetaType
    -0.69
    FormTagHelper
    -0.65
    yeezy
    -0.63
    while
    -0.62
     חיצוניים
    -0.62
    PAIGN
    -0.62
    diğinde
    -0.61
    POSITIVE LOGITS
     Dry
    1.09
    Dry
    1.05
     DRY
    1.03
     dry
    0.94
    DRY
    0.92
     wet
    0.92
    wet
    0.88
    Wet
    0.88
    dry
    0.86
     Wet
    0.85
    Activations Density 0.079%

    No Known Activations