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. 12012
    Prev
    Next
    INDEX
    Explanations

    references to conflict and struggle, particularly in relationships or power dynamics

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

    Tokens preceding pronouns "they" or "them."

    np_acts-logits-general · gemini-2.0-flash

    third-person plural pronouns

    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
    picas
    -0.47
    }>{
    -0.45
     his
    -0.43
     onun
    -0.43
     him
    -0.41
    ouncer
    -0.41
    自身の
    -0.40
    erval
    -0.40
    他在
    -0.39
    zji
    -0.38
    POSITIVE LOGITS
     them
    1.41
    They
    1.40
     they
    1.38
     They
    1.37
    they
    1.36
    彼らは
    1.34
    them
    1.34
     mereka
    1.32
    Mereka
    1.22
    他们
    1.21
    Activations Density 0.571%

    No Known Activations