© 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. 16-GEMMASCOPE-RES-16K
    6. 3907
    Prev
    Next
    INDEX
    Explanations

    references to the importance of relationships and connections between individuals or communities

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

    Abstract concepts around human connection

    np_acts-logits-general · gemini-2.0-flash

    emotional connections and bonds

    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
    RefNanny
    -0.66
     geslacht
    -0.60
    ItemLayout
    -0.59
    activités
    -0.58
     Busy
    -0.58
     calldata
    -0.58
    Hobbies
    -0.57
     Económica
    -0.57
    >>;
    -0.56
    Busy
    -0.56
    POSITIVE LOGITS
     intang
    0.68
     intangible
    0.65
     transcends
    0.64
     unique
    0.64
     magical
    0.63
     interaction
    0.62
     magic
    0.62
     visceral
    0.58
     capturing
    0.58
     emotional
    0.57
    Activations Density 0.336%

    No Known Activations