© 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. 9-GEMMASCOPE-RES-16K
    6. 9632
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "shift"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dundas
    -0.74
    Dund
    -0.73
     Waterhouse
    -0.72
    
    -0.69
    onavirus
    -0.69
    }{||
    -0.68
     ordenador
    -0.66
    мені
    -0.65
     Md
    -0.65
     Bradbury
    -0.65
    POSITIVE LOGITS
     SHIFT
    1.73
     shift
    1.70
     Shift
    1.64
     shifts
    1.61
     Shifts
    1.59
    hift
    1.59
    shifts
    1.53
    shift
    1.52
    Shift
    1.47
    SHIFT
    1.45
    Activations Density 0.074%

    No Known Activations