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. 14-GEMMASCOPE-RES-16K
    6. 10643
    Prev
    Next
    INDEX
    Explanations

    instances where analysis or evaluation occurs, particularly in contexts discussing effectiveness or response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.63
    🏻‍♀️
    -0.61
    arne
    -0.59
     nahilalakip
    -0.57
    ])));
    -0.57
    '){
    
    -0.56
    )()
    -0.55
     Sey
    -0.55
     '
    
    -0.54
     =
    
    -0.54
    POSITIVE LOGITS
     this
    1.28
     these
    1.17
    this
    0.93
    these
    0.84
     queste
    0.84
     acestui
    0.82
     questa
    0.81
     этих
    0.81
     این
    0.81
     questo
    0.80
    Activations Density 0.688%

    No Known Activations