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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 6727
    Prev
    Next
    INDEX
    Explanations

    references to various interests and the implications they have within contexts such as politics, economics, and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SARS
    -0.61
     aside
    -0.59
     "..\..\..\
    -0.58
    AnchorTagHelper
    -0.56
    omock
    -0.56
    UPAC
    -0.56
    
    -0.54
    kadot
    -0.54
    HTTPResponse
    -0.53
    SARS
    -0.53
    POSITIVE LOGITS
     interests
    2.52
    interests
    2.14
     Interests
    2.03
    Interests
    1.76
     Interessen
    1.41
     intereses
    1.34
     interesses
    1.32
     intérêts
    1.06
     pursuits
    0.98
     kepentingan
    0.95
    Activations Density 0.095%

    No Known Activations