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. 8571
    Prev
    Next
    INDEX
    Explanations

    economic terms related to stability and fluctuations

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

    followed by a comma or period

    np_acts-logits-general · gemini-2.0-flash

    modal verbs and auxiliary verbs

    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
     myſelf
    -1.02
     Efq
    -0.95
     purpoſe
    -0.95
     ſeveral
    -0.93
     themſelves
    -0.91
     pleaſure
    -0.91
    awtextra
    -0.87
     leaſt
    -0.86
     ſever
    -0.85
     Monfieur
    -0.85
    POSITIVE LOGITS
     is
    1.89
     has
    1.60
     was
    1.54
     will
    1.50
     can
    1.43
     might
    1.35
     could
    1.35
     may
    1.35
     would
    1.27
     must
    1.23
    Activations Density 1.592%

    No Known Activations