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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15704
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with economic decline and recovery

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

    a return to a previous state

    np_acts-logits-general · gemini-2.0-flash

    return to a better state

    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
    liss
    -0.49
     Subtract
    -0.43
    bin
    -0.41
    قيقة
    -0.40
    htdocs
    -0.40
    enski
    -0.39
    agua
    -0.39
    プリ
    -0.39
    unning
    -0.39
    riba
    -0.38
    POSITIVE LOGITS
     recovery
    2.01
     recovers
    1.86
     recovered
    1.81
     recover
    1.79
     restored
    1.79
     revival
    1.78
     regained
    1.76
     regaining
    1.75
     revived
    1.74
     restoration
    1.72
    Activations Density 0.500%

    No Known Activations