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. 25-GEMMASCOPE-RES-16K
    6. 4272
    Prev
    Next
    INDEX
    Explanations

    phrases related to political issues and candidates' positions

    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
    TargetException
    -0.62
     Roskov
    -0.55
    تقاوى
    -0.54
    HostException
    -0.53
    enterOuterAlt
    -0.52
    msgTypes
    -0.51
     rangs
    -0.50
    writeField
    -0.50
    ########.
    -0.49
    лыша
    -0.49
    POSITIVE LOGITS
     issues
    1.59
     topics
    1.30
    issues
    1.20
     questions
    1.20
     Issues
    1.19
     matters
    1.13
    Issues
    1.12
     subjects
    1.12
     thorny
    1.12
     pressing
    1.09
    Activations Density 0.495%

    No Known Activations