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. 3216
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal needs and requests

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

    Following personal pronouns in other languages

    np_acts-logits-general · gemini-2.0-flash

    utility, purpose, or assignment

    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
     ligiloj
    -0.58
    Enllaces
    -0.51
     متعلقه
    -0.49
    ConfigureAwait
    -0.48
     JpaRepository
    -0.47
    WebMethod
    -0.47
     ProtoMessage
    -0.46
     CreateTagHelper
    -0.46
     conosco
    -0.45
     Reasoning
    -0.44
    POSITIVE LOGITS
    AnchorStyles
    0.67
    seille
    0.65
     surla
    0.62
     piace
    0.62
     ascribed
    0.61
     assigned
    0.60
    ########.
    0.58
     assigning
    0.58
     Paglinawan
    0.57
     owe
    0.57
    Activations Density 0.038%

    No Known Activations