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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 393
    Prev
    Next
    INDEX
    Explanations

    discussions or mentions of hypothetical situations or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liferay
    -0.78
    最快更新
    -0.71
    Britt
    -0.70
     Britt
    -0.67
    histle
    -0.66
     Biss
    -0.66
    HomeAsUp
    -0.65
    IBinder
    -0.64
    staun
    -0.63
    Lack
    -0.62
    POSITIVE LOGITS
    scenarios
    1.69
     Scenario
    1.63
     scenarios
    1.63
     Scenarios
    1.59
     scenario
    1.58
    Scenario
    1.55
    scenario
    1.52
    cenario
    1.34
    rungsseite
    1.22
    Scen
    0.95
    Activations Density 0.080%

    No Known Activations