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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11665
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and party affiliations in the context of nominations and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.70
    Sklici
    -0.41
    AndroidJUnit
    -0.41
    
    -0.38
    ronpa
    -0.38
     mut
    -0.35
     büyü
    -0.35
    guantes
    -0.35
     iyong
    -0.34
    corder
    -0.33
    POSITIVE LOGITS
     OMITBAD
    0.61
     InputDecoration
    0.60
     candidate
    0.59
     candidates
    0.56
     kandid
    0.54
    thâu
    0.52
     Candidate
    0.50
     Candidates
    0.50
    Candidates
    0.50
    candidate
    0.50
    Activations Density 0.380%

    No Known Activations