© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10982
    Prev
    Next
    INDEX
    Explanations

    keywords related to marketing and political campaigning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.41
    ratos
    -0.33
     Laws
    -0.33
    principalColumn
    -0.33
    Consumes
    -0.32
    ViewChild
    -0.32
     Hore
    -0.31
    ResponseWriter
    -0.31
    bodyParser
    -0.31
    TProtocol
    -0.31
    POSITIVE LOGITS
     propaganda
    0.63
    tanleria
    0.60
     tagline
    0.56
     propagan
    0.56
     advertising
    0.55
     stressing
    0.54
     advertise
    0.53
     marketed
    0.52
     claiming
    0.52
     appealing
    0.52
    Activations Density 0.564%

    No Known Activations