© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10803
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss overall situations or summarize events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    const
    -0.58
    mit
    -0.54
    n
    -0.45
    (
    -0.45
    0
    -0.44
     habet
    -0.44
    dite
    -0.43
    from
    -0.43
     seine
    -0.41
    ec
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.98
    Tudo
    0.92
    IUrlHelper
    0.89
     transférez
    0.82
     Tudo
    0.82
     مشين
    0.80
     فريبيس
    0.79
    ^(@)
    0.78
     متعلقه
    0.77
    脚注の使い方
    0.76
    Activations Density 0.316%

    No Known Activations