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. 12439
    Prev
    Next
    INDEX
    Explanations

    information related to software updates and their details

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

    Software updates or version releases

    np_acts-logits-general · gemini-2.0-flash

    software updates and versions

    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
    AnchorStyles
    -0.50
     NUKAT
    -0.47
    indakan
    -0.46
    $_['
    -0.46
     real
    -0.45
     pé
    -0.45
    rungsseite
    -0.44
    flex
    -0.44
     virtuel
    -0.44
    WPF
    -0.43
    POSITIVE LOGITS
     version
    0.85
     versions
    0.82
     Versions
    0.82
     Version
    0.80
     upgrade
    0.80
     firmware
    0.77
     latest
    0.76
     upgraded
    0.76
    Versions
    0.74
     upgrades
    0.73
    Activations Density 0.586%

    No Known Activations