© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6335
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence or effects of factors that influence phenomena

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

    "but also"

    np_acts-logits-general · gemini-2.0-flash

    but also

    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
    ícil
    -0.70
    minecraft
    -0.64
    Filmografia
    -0.61
    openzeppelin
    -0.60
    AnimationFrame
    -0.59
    thane
    -0.58
    URIComponent
    -0.57
    apimachinery
    -0.56
    واره
    -0.56
    bingen
    -0.55
    POSITIVE LOGITS
     also
    4.56
    also
    3.76
    Also
    3.47
     Also
    3.38
     también
    3.24
     também
    3.21
     также
    3.08
     également
    2.96
     juga
    2.95
     ALSO
    2.93
    Activations Density 2.793%

    No Known Activations