© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2328
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluating conditions or states

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

    and phrases indicating positivity

    np_acts-logits-general · gemini-2.0-flash

    feel good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COUVER
    -0.59
     TextInputType
    -0.59
    +#+#
    -0.57
    ParallelGroup
    -0.53
    QMetaType
    -0.52
     EdgeInsets
    -0.48
     BoxFit
    -0.48
     EconPapers
    -0.47
    Revenir
    -0.46
     springfox
    -0.45
    POSITIVE LOGITS
     good
    3.79
    good
    3.38
    Good
    3.02
     Good
    2.88
     GOOD
    2.82
    GOOD
    2.72
     buena
    2.24
     buenas
    2.16
     gute
    2.08
     buenos
    2.08
    Activations Density 0.513%

    No Known Activations