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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5893
    Prev
    Next
    INDEX
    Explanations

    calls for government action and funding in response to social and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.70
    Enllaces
    -0.69
    UnknownFields
    -0.63
    HasAnnotation
    -0.63
     Normdatei
    -0.63
    AddTagHelper
    -0.62
     MainAxisSize
    -0.61
    runApp
    -0.60
    脚注の使い方
    -0.58
    спонд
    -0.58
    POSITIVE LOGITS
     urgently
    1.07
     urgente
    1.05
     endlich
    0.97
     urgent
    0.89
     dringend
    0.87
     seriously
    0.83
    reszcie
    0.79
     urgency
    0.78
     serious
    0.77
    urgent
    0.76
    Activations Density 0.386%

    No Known Activations