© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15919
    Prev
    Next
    INDEX
    Explanations

    concepts related to survival and persistence

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

    phrases describing someone or something remaining in a location or staying put.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.56
    Jeografia
    -0.49
    "}")
    -0.47
    {};
    -0.46
     Simult
    -0.46
     instantaneous
    -0.46
     مرئيه
    -0.46
    SourceChecksum
    -0.45
     flash
    -0.45
     rapid
    -0.43
    POSITIVE LOGITS
     longer
    1.23
     indefinitely
    1.03
    longer
    1.00
    Longer
    0.88
     Longer
    0.87
     dłu
    0.85
     longest
    0.84
     länger
    0.78
     forever
    0.73
     längre
    0.72
    Activations Density 0.419%

    No Known Activations