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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14427
    Prev
    Next
    INDEX
    Explanations

    commands and verbs related to action and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.88
    wahati
    -0.66
     linkovi
    -0.65
    ➯
    -0.64
    PasswordEncoder
    -0.64
    Спољашње
    -0.63
    yargs
    -0.62
    quite
    -0.61
    akukan
    -0.60
     ElementRef
    -0.60
    POSITIVE LOGITS
     yourself
    1.06
     your
    1.02
     yourselves
    0.78
     Yourself
    0.76
    able
    0.75
     me
    0.74
     gärna
    0.74
     them
    0.71
     gjerne
    0.69
    lah
    0.63
    Activations Density 0.470%

    No Known Activations