Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116242
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recover" and its derivatives, indicating a focus on the theme of recovery

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

    recover from or recover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     /*#__
    -0.56
     Wren
    -0.55
     Sirius
    -0.52
     JUN
    -0.51
    lineWidth
    -0.50
     ultimatum
    -0.50
     Avenue
    -0.49
    XAxis
    -0.49
     Jays
    -0.48
    mjs
    -0.48
    POSITIVE LOGITS
     recover
    1.01
     recovery
    0.95
    Recovery
    0.93
    recovery
    0.93
    Recover
    0.93
     Recover
    0.93
     Recovery
    0.91
     recuperação
    0.91
    recover
    0.88
     RECOVERY
    0.87
    Activations Density 0.018%

    No Known Activations