© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11984
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and systems in various technical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Subject followed by a state of being

    np_acts-logits-general · gemini-2.0-flash

    noun followed by state or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     probably
    -0.47
    Probably
    -0.45
     Probably
    -0.42
     sure
    -0.42
    Gambas
    -0.40
    Geplaatst
    -0.40
    probably
    -0.39
    ∮
    -0.36
     tentu
    -0.35
     certainly
    -0.35
    POSITIVE LOGITS
     fails
    0.76
     succeeds
    0.70
     becomes
    0.67
     reaches
    0.64
     fail
    0.59
     exceeds
    0.58
     prevails
    0.57
     progresses
    0.56
     happens
    0.56
     arrives
    0.54
    Activations Density 0.887%

    No Known Activations