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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14733
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles and their authors in an academic context

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

    Commas within scientific publications and numbers

    np_acts-logits-general · gemini-2.0-flash

    citations and academic references

    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
    .
    -0.57
    1
    -0.57
    ,
    -0.57
    3
    -0.56
     (
    -0.55
     a
    -0.54
     in
    -0.53
    2
    -0.52
     
    -0.51
    -
    -0.51
    POSITIVE LOGITS
    tvguidetime
    1.11
    expandindo
    1.04
     bezeichneter
    1.03
     itſelf
    0.97
     Shakspeare
    0.94
     Efq
    0.93
     ་་
    0.92
     iſt
    0.92
     ſever
    0.90
     дописавши
    0.87
    Activations Density 0.711%

    No Known Activations