© 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. 6-GEMMASCOPE-RES-16K
    6. 2285
    Prev
    Next
    INDEX
    Explanations

    references to returning or bringing something back

    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
    contentLoaded
    -0.64
    PasswordEncoder
    -0.60
    MeasureSpec
    -0.59
    CodeAnalysis
    -0.58
     springfox
    -0.57
    multer
    -0.55
    etz
    -0.55
    alsy
    -0.54
    هداف
    -0.54
    WebVitals
    -0.53
    POSITIVE LOGITS
     reinstate
    1.02
     restore
    1.00
     regaining
    0.99
     restoring
    0.97
     reinstatement
    0.96
     regain
    0.95
     restored
    0.94
     regained
    0.93
     reactiv
    0.92
     restoration
    0.92
    Activations Density 0.236%

    No Known Activations