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. 20-GEMMASCOPE-RES-16K
    6. 3128
    Prev
    Next
    INDEX
    Explanations

    elements and concepts related to data management and digital file handling

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

    Plural nouns followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    contained or located

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.52
    是对
    -0.48
    зму
    -0.43
     nue
    -0.40
     NgModule
    -0.40
    HomeAsUpEnabled
    -0.39
     Where
    -0.39
    PREFERRED
    -0.38
    的对
    -0.37
    zeczytaj
    -0.37
    POSITIVE LOGITS
     located
    1.36
     contained
    1.25
     housed
    1.23
     residing
    1.22
     znajdu
    1.20
     situated
    1.17
     موجود
    1.13
    located
    1.11
     stationed
    1.08
    contained
    1.07
    Activations Density 0.837%

    No Known Activations