© 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 EvalsExportsinterp-engineNEWAPI 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. 1630
    Prev
    Next
    INDEX
    Explanations

    phrases related to product evaluation and user experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hedging phrases and personal opinions

    np_acts-logits-general · gemini-2.0-flash

    state or condition

    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
    Not in Any Lists

    No Comments

    Negative Logits
     lecz
    -0.69
     posiada
    -0.69
     אשר
    -0.63
     endast
    -0.61
     utilizing
    -0.61
    慢慢的
    -0.60
     Utilizing
    -0.57
     iż
    -0.55
     gdyż
    -0.54
     didalam
    -0.54
    POSITIVE LOGITS
     weirdly
    0.79
     goddamn
    0.79
     ostensibly
    0.69
    というわけで
    0.68
     stuff
    0.68
     variously
    0.68
     kinds
    0.66
     weird
    0.65
     shitty
    0.65
     IIRC
    0.65
    Activations Density 4.178%

    No Known Activations