© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9179
    Prev
    Next
    INDEX
    Explanations

    phrases about relationships and connections between people

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

    Followed by an adverb or preposition

    np_acts-logits-general · gemini-2.0-flash

    offered or offered

    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
     {
    -0.47
    葩
    -0.44
    xido
    -0.42
    شن
    -0.42
     surf
    -0.42
    >
    -0.41
    cara
    -0.41
    Leipzig
    -0.41
     Tiki
    -0.41
     Ams
    -0.40
    POSITIVE LOGITS
     mergeFrom
    0.99
     تضيفلها
    0.97
    expandindo
    0.97
    AndEndTag
    0.93
    :+:
    0.88
    basicConfig
    0.83
     مشين
    0.82
    出版年
    0.80
    ########.
    0.75
    
    0.74
    Activations Density 1.268%

    No Known Activations