© 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. 8-GEMMASCOPE-RES-16K
    6. 6165
    Prev
    Next
    INDEX
    Explanations

    expressions related to lifting or raising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -1.01
    extAlignment
    -0.96
     Pyle
    -0.90
    +:+
    -0.90
    contentValues
    -0.89
    HandlerContext
    -0.88
     Проци
    -0.87
    MemoryWarning
    -0.85
    aarrggbb
    -0.84
    ništvo
    -0.83
    POSITIVE LOGITS
     lift
    1.46
     LIFT
    1.44
     lifting
    1.40
     lifted
    1.39
     Lift
    1.38
     lifts
    1.38
    Lift
    1.27
    lift
    1.16
     Lifting
    1.16
    Lifting
    1.05
    Activations Density 0.094%

    No Known Activations