© 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. 6836
    Prev
    Next
    INDEX
    Explanations

    terms related to recovery and saving situations

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

    rescuing or saving

    np_acts-logits-general · gemini-2.0-flash

    rescuing or saving people

    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
     defaultstate
    -0.60
    setVerticalGroup
    -0.59
     Exactos
    -0.55
    ikita
    -0.54
    WebControls
    -0.54
    OGND
    -0.54
     initComponents
    -0.52
     CreateTagHelper
    -0.50
    čenje
    -0.48
    ğren
    -0.47
    POSITIVE LOGITS
     saved
    2.45
     saving
    2.44
     rescue
    2.41
     save
    2.32
     saves
    2.26
     rescuing
    2.17
     Saving
    2.09
    saving
    2.07
    save
    2.04
    Saving
    2.04
    Activations Density 0.262%

    No Known Activations