© 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. 0-GEMMASCOPE-RES-16K
    6. 8023
    Prev
    Next
    INDEX
    Explanations

    terminology related to regulations or conditions concerning financial exchanges and mutual funds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.42
    ͘
    -0.40
    QMetaType
    -0.40
    mators
    -0.37
    PerformLayout
    -0.37
     Koy
    -0.36
    PropertyGroup
    -0.36
    itarianism
    -0.36
     Commands
    -0.36
    انگلیسی
    -0.36
    POSITIVE LOGITS
     mutual
    0.85
     mutually
    0.80
     sto
    0.75
     Sto
    0.71
     jointly
    0.71
     Mutual
    0.71
    mutual
    0.70
    Sto
    0.69
    Mutual
    0.66
     joint
    0.59
    Activations Density 1.512%

    No Known Activations