Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3777
    Prev
    Next
    INDEX
    Explanations

    terms related to digital technology and industrial applications

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

    after commas, and/or managing

    np_acts-logits-general · gemini-2.0-flash

    managing relationships and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.74
     
    -0.73
     in
    -0.69
    ,
    -0.67
     on
    -0.65
     to
    -0.64
     a
    -0.64
    -
    -0.62
     at
    -0.61
     (
    -0.60
    POSITIVE LOGITS
    AddHtmlAttribute
    1.39
     ་་
    1.23
     ſind
    1.23
     ―――――
    1.21
     Theſe
    1.19
     itſelf
    1.18
     Monfieur
    1.17
     iſt
    1.17
     تضيفلها
    1.17
     الحره
    1.15
    Activations Density 0.670%

    No Known Activations