© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9720
    Prev
    Next
    INDEX
    Explanations

    terms related to software architecture and framework systems

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

    after certain punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    certain words or titles

    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
     un
    -0.89
     ten
    -0.84
     pu
    -0.80
     ha
    -0.77
     pas
    -0.75
     bo
    -0.74
     hal
    -0.73
     ba
    -0.73
     so
    -0.73
     such
    -0.72
    POSITIVE LOGITS
     Houſe
    1.46
     Jefus
    1.43
    ſelves
    1.37
     Reſ
    1.33
     Eſ
    1.31
     Anſ
    1.30
    ſelf
    1.29
     Monfieur
    1.28
     Efq
    1.24
     itſelf
    1.23
    Activations Density 1.380%

    No Known Activations