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. 13-GEMMASCOPE-RES-16K
    6. 330
    Prev
    Next
    INDEX
    Explanations

    terms related to rear-view camera systems and backing visibility

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

    references to rear or back parts of objects, particularly vehicles and cameras.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.83
    ingway
    -0.79
    DebuggerNonUser
    -0.77
    Хьажоргаш
    -0.75
    gouv
    -0.69
     autorytatywna
    -0.68
     mite
    -0.68
     ویکی‌پدیای
    -0.67
    MessageTagHelper
    -0.66
     cloche
    -0.65
    POSITIVE LOGITS
    cipital
    0.92
     backs
    0.89
     Hinter
    0.86
    PostExecute
    0.84
     tail
    0.82
    BackStack
    0.79
     backside
    0.78
    Rear
    0.78
     Rear
    0.77
     rear
    0.76
    Activations Density 0.168%

    No Known Activations