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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2914
    Prev
    Next
    INDEX
    Explanations

    instances of the word "saved" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebRequest
    -0.81
    WithMany
    -0.66
    toje
    -0.59
    antMatchers
    -0.58
    createCanvas
    -0.57
    AndUpdate
    -0.57
    autant
    -0.56
     @"/
    -0.56
    XmlAccessType
    -0.56
    -------------</
    -0.56
    POSITIVE LOGITS
    saved
    2.02
     saved
    1.86
     Saved
    1.70
    Saved
    1.64
     saving
    0.92
     Saving
    0.88
    savings
    0.87
     saves
    0.87
     savings
    0.84
     SAV
    0.82
    Activations Density 0.179%

    No Known Activations