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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12030
    Prev
    Next
    INDEX
    Explanations

    snippets of code involving file and directory manipulation

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

    Code snippets and less common English words

    np_acts-logits-general · gemini-2.0-flash

    citizen case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.73
     Alba
    -0.56
    -
    -0.55
     heng
    -0.55
     sc
    -0.55
     Jack
    -0.54
    ER
    -0.54
    lievo
    -0.54
     bu
    -0.53
    י
    -0.52
    POSITIVE LOGITS
     chofe
    1.21
     Anſ
    1.15
     myſelf
    1.14
     Houſe
    1.11
     fubject
    1.11
     Eſ
    1.10
     uſed
    1.10
     reaſon
    1.09
     cauſe
    1.09
     againſt
    1.08
    Activations Density 0.098%

    No Known Activations