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. 0-GEMMASCOPE-RES-16K
    6. 9829
    Prev
    Next
    INDEX
    Explanations

    references to breasts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.73
    .
    -0.72
     
    -0.71
    ,
    -0.68
     The
    -0.65
    2
    -0.64
    at
    -0.64
    ↵
    -0.64
    1
    -0.63
     A
    -0.63
    POSITIVE LOGITS
     дописавши
    1.27
    GEBURTSDATUM
    1.22
    StoryboardSegue
    1.16
    RTLD
    1.14
     EconPapers
    1.13
    InputTagHelper
    1.10
    NUMX
    1.09
     Мексичка
    1.07
    ^(@)
    1.05
     itſelf
    1.04
    Activations Density 0.080%

    No Known Activations