© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15609
    Prev
    Next
    INDEX
    Explanations

    phrases related to applications for jobs or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *)((
    -0.55
    InteropServices
    -0.54
     })
    
    -0.53
     feeding
    -0.48
    korb
    -0.48
     }).
    -0.48
     EdgeInsets
    -0.46
     disposer
    -0.46
    feed
    -0.45
    BeginContext
    -0.45
    POSITIVE LOGITS
     application
    1.52
     applicants
    1.47
     Application
    1.46
     applicant
    1.45
     applications
    1.42
     Applicants
    1.42
     Applications
    1.38
    Application
    1.35
    APPLICATION
    1.32
     Applicant
    1.32
    Activations Density 0.335%

    No Known Activations