© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 82685
    Prev
    Next
    INDEX
    Explanations

    arrays and JSON-like structures in programming contexts

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

    function return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -1.05
     houſe
    -1.03
    :✨
    -1.02
    ſelves
    -1.00
     Verſ
    -0.98
     Houſe
    -0.98
     ſche
    -0.98
    transQ
    -0.93
     ſta
    -0.92
     disambiguazione
    -0.91
    POSITIVE LOGITS
     
    0.45
    Then
    0.37
     I
    0.37
     puis
    0.36
     before
    0.36
    Затем
    0.33
     majd
    0.33
     Then
    0.33
     then
    0.33
    Before
    0.32
    Activations Density 0.069%

    No Known Activations