© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 593
    Prev
    Next
    INDEX
    Explanations

    positive sentiments related to political achievements and campaign effectiveness

    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
    انجليز
    -0.60
    netbeans
    -0.51
     AssemblyCulture
    -0.51
    UnknownFields
    -0.50
    LabelTagHelper
    -0.50
    :+:
    -0.47
     Explorers
    -0.44
    izzate
    -0.42
    はじめに
    -0.42
    TableAdapter
    -0.41
    POSITIVE LOGITS
     political
    1.99
     election
    1.92
     politics
    1.88
     voters
    1.84
     Election
    1.84
     elections
    1.81
     Political
    1.79
     voter
    1.77
     electoral
    1.77
    Political
    1.74
    Activations Density 1.743%

    No Known Activations