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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 30782
    Prev
    Next
    INDEX
    Explanations

    the term "inflate" in various contexts, likely related to layout or UI elements in programming

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

    repeated double field

    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
    RTEE
    -0.70
    Tikang
    -0.69
    /**
    -0.54
    transQ
    -0.50
     
    -0.49
     baseman
    -0.49
    <?
    -0.48
    clerosis
    -0.48
     réforme
    -0.47
    ectady
    -0.47
    POSITIVE LOGITS
    inflate
    2.52
     Inflate
    0.98
    Infl
    0.94
    setContentView
    0.92
     inflate
    0.84
    LayoutInflater
    0.76
     onCreateView
    0.69
     Infl
    0.67
     inflation
    0.65
    StoryboardSegue
    0.64
    Activations Density 0.000%

    No Known Activations