© 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. 20-GEMMASCOPE-RES-16K
    11. 495
    Prev
    Next
    INDEX
    Explanations

    connections between various subjects and actions, particularly in research contexts

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

    followed by research activities

    np_acts-logits-general · gemini-2.0-flash

    performing an action or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.70
    كتشاف
    -0.62
     nakalista
    -0.61
    initializeApp
    -0.61
    titleMargin
    -0.61
    setAdapter
    -0.60
     mapStateToProps
    -0.60
     ComVisible
    -0.58
    bonucle
    -0.58
    zzleHttp
    -0.58
    POSITIVE LOGITS
     conducting
    1.25
     undergoing
    1.19
    Conduct
    1.15
     melakukan
    1.13
     undergo
    1.13
    进行
    1.11
     conduct
    1.11
     Conducting
    1.10
     undertake
    1.10
     进行
    1.05
    Activations Density 0.776%

    No Known Activations