© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9478
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative procedures or discussions around policy decisions regarding missile alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.46
     imobili
    -0.40
    toronto
    -0.40
     costumi
    -0.39
    дарт
    -0.39
     secundario
    -0.39
    licone
    -0.39
     profession
    -0.39
    EClass
    -0.39
    zkod
    -0.39
    POSITIVE LOGITS
     legislative
    0.92
     Legis
    0.85
     legislators
    0.85
     Congressional
    0.83
     lawmakers
    0.83
     legislation
    0.83
     legislator
    0.82
     congressional
    0.82
     Senate
    0.81
     bipartisan
    0.81
    Activations Density 0.604%

    No Known Activations