© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 11821
    Prev
    Next
    INDEX
    Explanations

    the term "press" and its variations in different contexts

    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
    principalColumn
    -0.65
    jsii
    -0.56
    thâu
    -0.56
    tagHelper
    -0.56
    choon
    -0.54
     kaarangay
    -0.53
     الرياضيه
    -0.47
    biamo
    -0.47
     strerror
    -0.46
    brinco
    -0.46
    POSITIVE LOGITS
     pressed
    1.00
    press
    0.94
     compressed
    0.93
    PRESS
    0.92
     compress
    0.90
     compression
    0.89
    PRESSION
    0.87
     press
    0.85
    Press
    0.85
     presses
    0.85
    Activations Density 1.855%

    No Known Activations