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. 4128
    Prev
    Next
    INDEX
    Explanations

    references to companies, brands, and organizational entities

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

    Contacting or support from a company/entity

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and reflexive

    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
    adaptiveStyles
    -0.71
     CreateTagHelper
    -0.70
     distanciation
    -0.67
    GEBURTSDATUM
    -0.65
     nakalista
    -0.63
    andExpect
    -0.62
    UserScript
    -0.62
    󠁢
    -0.62
    extAlignment
    -0.61
    DataAnnotations
    -0.59
    POSITIVE LOGITS
     themselves
    2.23
    Their
    2.17
     their
    2.16
     Their
    2.06
    their
    1.90
    themselves
    1.77
     THEIR
    1.61
    他们的
    1.55
    他們的
    1.44
     leur
    1.39
    Activations Density 0.273%

    No Known Activations