© 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. 15-GEMMASCOPE-RES-16K
    11. 5290
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate controversy or disagreement within discussions and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yanka
    -0.60
    GeneratedCode
    -0.59
    WebControls
    -0.52
    brunn
    -0.50
    ViewFeatures
    -0.50
    Selanjutnya
    -0.49
    gestellt
    -0.49
     prochains
    -0.48
     تجمعات
    -0.48
    moveToFirst
    -0.48
    POSITIVE LOGITS
     conflicting
    1.08
     debated
    1.07
     debate
    1.07
     debates
    1.01
     dilemma
    1.01
     whether
    0.99
     debating
    0.97
     undecided
    0.96
     deciding
    0.94
     conflicted
    0.93
    Activations Density 0.550%

    No Known Activations